Japanese Idol Private Vlog
🔖 204 saves♥ 210 likes60sUGC & Vlog
Now available on EvoLink
Seedance 2.5 Prompts & Real Video Examples
Watch sourced results, pick the prompt behind them, and generate — Use carries the full prompt straight into the Seedance video generator.
Trending
High-save reusable prompts plus high-like visual standouts from X — saves signal reuse, likes signal immediate appeal.
UGC & Vlog
Hold a presenter’s identity and phone-camera realism across a full 30 seconds.
Handheld Travel Day Vlog
A friend-shot travel vlog that follows one woman through a full day, with imperfect framing and no scripted acting.
A realistic handheld travel vlog filmed by a friend following the main character throughout the day. Use the woman from the reference image as the main subject. Maintain her exact facial identity, hairstyle, facial features, and body proportions throughout the entire video. The camera feels like a real personal vlog camera, not a commercial production. Natural handheld movement, casual framing, imperfect human camera motion, authentic everyday atmosphere. No scripted acting. The woman behaves naturally, interacting with the environment like a real travel vlog. 0-5s: Morning departure. The woman leaves a cozy apartment with a small backpack. She checks her phone, smiles at the camera, adjusts her hair, and starts walking outside. The camera follows her from behind, slightly shaky like a friend filming. Morning sunlight, quiet neighborhood streets, people starting their day. 5-12s: Exploring the city. The camera follows her walking through local streets. She visits a small cafe, buys a drink, briefly talks to the camera, laughs naturally. She walks through a street market, looks at small shops, takes casual photos. The camera stays close, capturing spontaneous moments. 12-20s: Arriving at the beach. She takes public transportation or walks toward the coast. The environment gradually changes from city streets to a seaside town. Ocean breeze moves her hair. She looks excited when she sees the ocean. The camera follows her walking along the beach. She picks up a seashell, watches waves, and interacts naturally with people nearby. 20-27s: Summer beach afternoon. She meets friends at the beach. Everyone chats, laughs, plays near the water. The camera moves naturally between people, capturing real candid moments. She looks back at the camera and smiles. 27-30s: Ending moment. Golden hour sunset. She sits near the ocean, holding a drink, watching the sunset. The camera slowly moves backward, revealing the beach, waves, and the peaceful evening. A feeling of a real personal travel memory. Visual style: Authentic travel vlog footage. Realistic smartphone or mirrorless camera look. Natural daylight. Casual handheld movement. Slight camera shake. Real human reactions. Documentary realism. No cinematic commercial look. No dramatic posing. No artificial transitions. No text overlays. No logos. No face changes. No identity changes.
- Framing the camera operator as a friend, not a crew, tells the model how loose the handheld motion should be.
- Identity is locked once at the top, then every timed beat can change location without losing the subject.
- Explicitly ruling out scripted acting keeps the performance in vlog register rather than commercial register.
1 presenter referenceFull day, many scenesNo scripted acting
France 3AM Nightlife Handheld POV
A one-handed phone POV outside French bars at 3am, built from overlapping crowd noise, kebab queues and Uber waits rather than a story.
@dreamina_ai T2V prompt: A 30 second ultra realistic handheld POV video set in France at around 3 am, outside a busy bar and nightlife street. The camera is the point of view of a young woman filming one handed on an iPhone. We never see the phone itself at any point. The footage must feel like raw, authentic amateur nightlife footage with natural iPhone aesthetics. It is very late. People are leaving bars, smoking outside, waiting for Ubers, talking too loudly, eating kebabs, laughing in tired, sloppy groups. The mood in the street is a mix of drunken energy and visible exhaustion. Faces look tired, makeup is slightly worn, outfits are a bit messy after a long night. The pavement is slightly wet and reflects neon signs, headlights, and warm bar lights. The air feels cold and heavy. The whole scene must feel intensely real, socially awkward, and uncomfortable. The camera operator is a woman, and her friend is another young woman walking a few steps ahead of her, visibly angry. The camera follows her in a shaky, one-handed handheld way. The tension is already there from the first second. The argument is about the friend disappearing with a guy inside the bar and leaving the camera operator alone for nearly an hour, which made her miss the last train and feel abandoned. This is the core of the argument. The friend suddenly turns around while still walking and says in natural French from France: “Tu vas me suivre encore longtemps comme ça ?” The woman behind the camera replies, irritated and hurt: “Bah ouais, parce que tu m’as laissée toute seule comme une conne pendant une heure.” The friend rolls her eyes, tired and defensive: “Oh ça va, j’étais pas ‘avec un mec’, on parlait, c’est bon.” The camera gets a little closer as the woman filming answers immediately: “Mais arrête, tu m’as complètement lâchée. J’te cherchais partout.” The friend stops walking and turns fully toward the camera now, angry but exhausted: “J’allais pas te tenir la main toute la soirée non plus.” A few people nearby start glancing at them. Someone exits a bar laughing, a smoker looks over, a taxi passes in the background. The world keeps moving around them, but the argument becomes the emotional center of the scene. The woman filming replies, more intense now: “C’est pas ça le problème, le problème c’est que t’as disparu sans rien dire. J’ai raté le dernier train à cause de toi.” The friend laughs bitterly in disbelief: “À cause de moi ? Sérieux ? T’es incapable de te débrouiller toute seule ?” The camera jolts slightly from the emotional reaction. The breathing of the woman filming becomes more noticeable. Her voice gets sharper: “Mais t’abuses en fait. Tu fais toujours ça. Tu penses qu’à toi.” The friend steps closer, now visibly losing patience: “Et toi tu fais quoi là ? Tu me filmes en pleine rue comme une malade.” The woman behind the camera replies immediately: “Parce que tu racontes n’importe quoi !” The friend reaches toward the camera, not to grab a visible phone, but clearly trying to push it away from her face. The image jerks sideways hard from the contact. “Enlève ça de ma tête !” The camera operator snaps back: “Me touche pas !” Now the tension breaks completely. The friend, furious and emotionally overwhelmed, shouts: “Mais ferme-la un peu !” The woman filming fires back: “Sinon quoi ?!” There is a half-second pause. Heavy breathing. Eye contact directly into the lens. Then the friend lunges. She pushes into the camera operator. The footage becomes chaotic and violent, shaking hard as the woman filming loses balance. She lets out a shocked cry: “Putain !” The camera stumbles backward and drops toward the ground. As it falls, we catch blurred fragments: legs, jackets, streetlights, pavement, people turning around, someone shouting: “Eh oh ! Ça va pas ou quoi ?!” The friend jumps onto her as both fall out of balance. The camera lands badly on the ground, still recording for a split second, partly blocked by clothing or the ground. We hear struggling, overlapping voices, panic, and nearby people reacting. Then the video abruptly cuts. The entire performance must feel spontaneous, messy, and completely believable. Natural interruptions, overlapping dialogue, breath, hesitation, frustration, and tiny realistic body movements are essential. The acting must feel like a real late night argument between two exhausted friends, not a scripted drama. No cinematic polish, no stylized fight choreography, no slow motion, no music, no visible phone, no artificial lighting setup, and no glamorous performance. It must feel like a real one handed iPhone recording captured in the heat of the moment.
- Stating that the phone is never visible resolves the usual POV contradiction before it happens.
- The street is populated with specific late-night behaviours, so the crowd feels observed rather than generated.
- Amateur iPhone aesthetics are asked for as a capture mode, which keeps the grade and stabilisation honest.
30s handheld POVLayered crowd audioPhone-real texture
New York Self-Shot Day
A full New York day filmed by the subject herself, with named reference images fixing the hotel suite, wardrobe and locations.
SCENE A day in New York shot entirely by the subject herself: waking in her hotel suite, coffee, getting ready, out into the city, back to the room at night. ACTIVE REFERENCES @ image1 — the hotel suite. Curved cove ceiling with warm LED coving, deep red carpet, cream walls, two black organic sculptures above a light wood headboard, white bedding with red pillows, twin bedside lamps, pale sofa, oval coffee table, sheer curtains, dark door. @ image2 — the subject. Young woman, shoulder-length wavy blonde hair with curtain bangs and highlights, light freckles, thin gold necklace, silver ring, dark brown off-the-shoulder knit with white diamond-stripe pattern. 100% matches the reference. CAMERA OWNERSHIP LOCK Only two positions exist. HELD: arm extended, camera 0.4-0.7m from her face, visible arm tension, tilt and step-bounce. PROPPED: camera on a surface she placed it on, crooked and fixed, with her moving in and out of frame. No operator shots, no tracking, nothing she could not have filmed alone. FORMAT Eight shots, 30s, seven HARD CUTS, no fades. Real-time. 0-4s SHOT 1 — PROPPED, morning room. 84° diagonal field of view, camera on the sideboard 3m from the bed at 1.1m, static and tilted. The suite matches @ image1: cove light on, curtains half open, cool daylight across the red carpet. @ image2 visible at 0.0s, sitting up on the bed edge x66 y58. No empty frame. She rubs her face and croaks at the running camera: "It's seven. In New York. Why am I awake." Stands, walks out screen-right. HARD CUT. 4-7s SHOT 2 — HELD, window light. 84°, arm's length 0.5m, above eye line. She is x50 y42 at the sheer curtain screen-left, cool daylight on the near side of her face, cove warmth behind. She pulls the curtain, squints at the street below, then into the lens: "Okay. It's actually happening." Arm wobble throughout. HARD CUT. 7-11s SHOT 3 — PROPPED, coffee. 47°, camera on the oval coffee table 0.8m away, low, looking up past a cup. She sits into frame at x55 y45, pours, tastes, pulls a face at the running camera: "Hotel coffee. We'll fix that outside." Steam bends in the light. HARD CUT. 11-15s SHOT 4 — HELD, mirror. 47°, camera at chest height reflected in the suite mirror. She is x45 y50 in the reflection, camera visible in her hand, working through her hair with the other. Bed and sculptures behind. At 13s: "This is as good as it gets. Let's go." HARD CUT. 15-18s SHOT 5 — HELD, leaving. 107° wide rectilinear, camera held low at waist height, turned forward. She crosses the red carpet to the door at x55, lens swinging with her stride. She opens it and corridor light floods the frame. Off-frame, breathy: "Downtown first." HARD CUT. 18-22s SHOT 6 — PROPPED, street. 47°, camera on a stoop rail 3m away, static, crooked. A New York block behind her — brownstone steps, fire escapes, yellow cabs, steam from a vent. She walks in from screen-left at 18.5s, stands at x60 y50, spreads her arms: "Look at this street." Then walks to the lens and takes it at 21.5s. Passers-by cross the foreground. HARD CUT. 22-26s SHOT 7 — PROPPED, diner. 84° wide, camera on the counter behind a plate, 0.7m from her, looking up. She is x55 y38, sits into frame, takes a bite, eyes widen, mouth full: "Okay, that's the one." Laughs, keeps eating. HARD CUT. 26-30s SHOT 8 — HELD, night, back in the room. 84°, arm's length 0.5m, held above her. She lies back across the white bedding at x50 y55, hair spread, in the brown knit again. Bedside lamps and cove light are the only sources, windows black with city glow. Into the lens: "Twenty thousand steps. Everything hurts." Softer: "Same time tomorrow." Wave, the frame tilts as she lowers the camera. 30.0s black. SPEECH Only the quoted lines are spoken, at the timings given, all in her voice. Lips still at all other times. No voiceover, no second speaker, no offscreen voices. Delivery is casual, unrehearsed, mid-breath, sometimes trailing off. Volume rises over street noise in Shot 6, near-whisper in Shot 8. CONTINUITY The suite matches @ image1 in both interior sequences — same carpet, sculptures, headboard, sofa, lamps. Hair, necklace and ring identical throughout. PHYSICS Loose knit slides on the shoulder with every arm movement. Wavy hair lags a frame behind head turns. Bedding creases under her weight. Step energy visible in every HELD frame. LIGHTING Shots 1-4: cool daylight from the curtains screen-left as key, warm cove LED as fill, red carpet bouncing warmth into the shadows. Shot 5: corridor light through the doorway. Shots 6-7: hard street daylight, warm diner practicals. Shot 8: lamps and cove light only. AUDIO Diegetic only, from the same camera — room tone, footsteps, door, traffic, sirens, steam vents, diner clatter, wind. Ambience ducks under her lines. No music. LOCKS Photoreal live action, 4K detail, fine grain, warm consumer-camera colour, mild rolling shutter and auto-exposure hunting. She is the only person who speaks; background figures anonymous and unfocused. No subtitles. #Seedance25 #Seedance #VLOG #Higgsfield @higgsfield @noman23761 https://t.co/1uOx9ztM6r
- Active references are listed with their exact contents, so the suite looks identical every time she returns to it.
- The day is structured as a loop — wake, out, return at night — giving the footage a natural arc.
- Self-shot framing keeps the camera logic consistent across very different environments.
Named refs: suite · wardrobeSelf-shot across NYC29s
Casual Apartment Tour Phone Video
A vertical apartment tour filmed by a friend walking behind her, explicitly not cinematic and with no colour grade.
Vertical phone video, 30 seconds. A friend films a casual apartment tour on a smartphone, walking behind and beside her. Natural indoor daylight, handheld sway, clean modern phone footage. Not cinematic, no color grade, no professional lighting. SUBJECT: a woman in her late 20s @image1, warm deep brown skin, long dark box braids pulled half-up, gold hoop earrings, cream knit top, beige wide-leg trousers, relaxed and cheerful. Consistent appearance throughout. LOCATION: a bright, styled modern apartment, cream walls, oak floors, large windows with sheer curtains, houseplants, textured cushions, brass accents, a boucle armchair, an arched mirror. 0–7s: she walks ahead into the living room, turning back toward the camera with a laugh, with this voice @voice1: "Okay fine, we're doing this. Welcome in." 7–15s: the camera pans off her to sweep across the living room, her voice continuing off-frame: "This is where I basically live. That light in the afternoon is... unreal." 15–23s: she walks toward the dining area, the camera following behind her, then she turns and gestures at the wall: "This part used to be completely bare. It looked like nobody lived here." 23–30s: she leans against the counter, smiling at the camera: "Got a design team in and they nailed it first try. I Didn't have to explain myself twice." She laughs and waves the camera off. AUDIO: room ambience, footsteps on wood, warm natural speech with pauses and laughter, faint street sound. No music. FORBIDDEN: no gimbal stabilization, no color grading, no film grain, no studio lighting, no subtitles, no music.
- Stating not cinematic, no grade, no professional lighting removes three defaults in one line.
- The operator's position — behind and beside her — sets a consistent walking geometry.
- Wardrobe and styling are fully specified, which keeps identity stable through a moving tour.
Vertical phone tourFriend-shot walking POVNo colour grade
Quiet Laundry Morning Home Vlog
A 15-second seven-shot phone-footage vlog of a woman doing laundry alone, with a single spoken line and natural window light.
15s handheld home-video vlog, 7-shot montage. Photorealistic phone footage with slight tilt, natural shake, window light, subtle film grain. A woman (use Image1 only for facial identity and hairstyle) does laundry alone on a quiet morning. Outfit: oversized cream linen shirt with rolled sleeves, grey knit shorts, loose cotton apron. Cozy sunlit laundry nook with an open front-load washer, overflowing basket, wooden drying rack, clothespins, and warm sunlight. She is the only person in the video. Sequence: untangles wet clothes → shakes out a shirt → checks a collar stain by the window → hangs it saying "Good enough." → finds a mismatched sock → struggles with a heavy bedsheet while laughing → finishes hanging it and quietly admires the sunlit laundry. Dialogue is natural spoken Korean (except "Good enough"), reacting casually to each moment. Ambient sound only: washer winding down, wet fabric, clothespins, rustling clothes, soft laughter, breeze. No subtitles, text, logos, or watermarks. Do not recreate or copy the reference image—use it only for facial identity and hairstyle.
- Seven short beats in 15 seconds give the montage a rhythm without any of them needing to be staged.
- Asking for phone-camera imperfections — tilt, shake, grain — is what stops the shot from looking rendered.
- One short line of dialogue is enough to make the scene feel lived-in without forcing lip-sync across the whole clip.
Kite-Flying Camcorder ASMR Vlog
A self-shot mini-DV camcorder vlog of flying a kite, built around fabric flap, spool unwind and wind on the microphone.
CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bright open-sky daylight. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic rather than polished cinematic footage. STYLE: Cozy outdoor kite-flying vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments, natural pauses. Focus on satisfying everyday sounds: kite fabric flapping in the wind, string spool unwinding, grass rustling underfoot, light breeze against the microphone. SUBJECT: Young woman in her mid-20s, plain windbreaker, hair tied back in a loose ponytail, minimal jewelry, no visible logos or branded items. Cheerful, carefree energy on a breezy afternoon. SETTING: Small open field on a bright breezy afternoon. Wide open sky, plain grass field, no visible signage, buildings with branding, or logos anywhere in frame. STORYBOARD: → (3s, propped medium shot) Places camera on a low tripod in the grass, unrolls a plain kite. "Perfect windy day for this." → (3s, overhead shot) Unwinds the string spool, checking it's free of tangles. → (3s, close-up) Attaches the string firmly to the kite frame. → (3s, handheld shot) Walks backward a few steps, testing the wind direction. "Feels strong enough today." → (3s, detail shot) Releases the kite gently into the air. No dialogue. → (3s, medium shot) Watches it climb higher, letting the string out slowly. "There it goes." → (3s, macro shot) Kite fabric flapping steadily against the open sky. → (3s, propped shot) Sits down on the grass, holding the string loosely. → (3s, warm ending shot) Looks up at the kite soaring, happy smile. "Love days like this." → (5s, final shot) Reels the string in slowly, glances toward camera. "See you next time." Reaches down and covers the lens as recording ends. AUDIO NOTES: Natural outdoor ambience — kite flapping, string unwinding, breeze, grass rustling should be clearly audible. Dialogue quiet and casual, as if speaking to a small personal audience. REALISM NOTES: Authentic body language, natural blinking, genuine cheerful smiles, occasional pauses adjusting the string, imperfect framing, focus breathing, bright open-sky lighting shifts. No copyrighted characters, logos, brand names, or recognizable public figures anywhere in frame. Fully original personal vlog content, not AI-generated or commercial in style.
- Camera flaws are specified as a list — focus hunting, exposure shifts, imperfect framing — which is what produces the camcorder look.
- The sound design is treated as the subject rather than an afterthought, so the model foregrounds the small textures.
- Minimal dialogue and natural pauses leave room for the ambience the prompt is actually asking for.
Hawaii Tropical Travel Vlog
A high-engagement Hawaii travel diary that holds one traveler across eight distinct city, beach, ocean, market, sunset, and hotel scenes.
Create a cinematic 30-second tropical travel vlog featuring the same 20-year-old East Asian woman with dark hair throughout every scene. Keep her facial identity, hairstyle, natural makeup and body proportions consistent. Use authentic handheld travel-diary movement, candid performance, soft golden-hour light, natural skin texture, shallow depth of field, warm vintage colour and subtle 35mm grain. 0-4s: follow her through a bright palm-lined Hawaiian street, then move into a windblown close-up. 4-8s: barefoot shoreline walk with low-angle footprints, ocean reflections and volcanic mountains. 8-12s: look up through palms into lens flare, then cut to her profile beside a rocky ocean cliff. 12-16s: quiet beachfront cafe details and a tropical drink by the window. 16-20s: water-level orbit as she floats and laughs on a surfboard in turquoise water. 20-24s: handheld night-market exploration with fruit skewers, local food, lanterns and neon bokeh. 24-27s: wide silhouette at an orange-pink ocean sunset. 27-30s: hotel balcony over tropical city lights, ending on an intimate peaceful close-up. Preserve documentary realism and natural autofocus changes. No CGI look, plastic skin, identity drift, distorted anatomy, duplicate people, oversaturation, blurry face, text or logos.
- Eight timed scenes give a multi-location travel montage a complete day arc instead of a collection of disconnected beauty shots.
- The traveler identity and image texture are locked before the timeline, protecting continuity while the locations change.
- Concrete camera imperfections keep the luxury imagery readable as a personal vlog rather than a polished brand commercial.
Japanese Idol Private Vlog
A one-minute Japanese idol diary that keeps one performer recognizable through candid home, pet, food, transit, rehearsal, and nighttime moments.
Create a one-minute Japanese-style idol personal vlog following the same young performer through a private day. Keep her face, hairstyle, wardrobe logic and personality consistent. The footage should feel self-shot or casually filmed by a close friend: handheld phone framing, small focus misses, ordinary room light, natural pauses, playful reactions and clean native ambience. Structure the minute as a personal diary: a direct-to-camera morning greeting at home; relaxed breakfast and getting-ready details; a candid moment playing with her fluffy cat; a quick convenience-store or cafe food stop; handheld travel between locations; rehearsal-room preparation and short performance fragments; an unguarded backstage break; and a quiet nighttime sign-off. Let her occasionally address the camera in natural Japanese, but avoid subtitles and on-screen text. Preserve believable lip sync, room tone and changes in acoustic space. No commercial posing, glamour-ad lighting, face drift, duplicate subject, plastic skin, distorted hands, floating props, logos or captions.
- A full-day diary structure gives the one-minute duration enough progression without turning it into a conventional narrative short.
- The same performer is explicitly locked across home, transit and rehearsal locations where identity drift is most likely.
- Self-shot imperfections, native ambience and direct camera address reproduce the intimacy viewers expect from idol vlog content.
DV Camcorder Self-Shot Day
A tape-camcorder POV where the subject films herself across several locations, with the camera itself never appearing on screen.
**CAMERA:** DV 16mm tape camcorder handheld feel. POV of CHASE holding the camera herself throughout each location, occasionally propped briefly for hands-free moments. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder never appears on screen. **LOOK:** Soft, slightly blurry tape quality, faint tape noise, bloomed highlights, flickering auto-exposure, muted contrast, realistic skin tones — lighting shifts per location (dim early-morning dorm → fluorescent vocal room → mirror-lit practice room → stark evaluation room lighting). **STYLE:** Nostalgic, determined montage feel — younger, rawer energy than her current polished vlogs, evoking a flashback to trainee days. Quick cuts stitched across locations, reflective voiceover narration plays over the visuals instead of synced dialogue. Mood shifts from tired to focused to nervous, ending on quiet resolve. **Character** CHASE — Korean trainee (ref image), late teens/early 20s (younger, flashback version of herself). Long straight black hair, often in a simple ponytail or braid, minimal to no makeup, tired but determined eyes. Wearing simple practice clothes — a plain long-sleeve top and joggers or sweats, fully covering arms and torso, no jewelry. **Setting Progression** Trainee dorm room (early morning) → vocal lesson room (morning) → dance practice room (afternoon) → evaluation room (evening). **Storyboard (15s, 5 cuts)** 1. *(~3s, dorm, propped camera, dim early light)* She wakes up before sunrise, rubbing her eyes, quietly getting ready in the dark so as not to wake roommates. VOICEOVER (CHASE): "Back then, mornings started before the sun even came up." 2. *(~3s, vocal room, handheld, fluorescent light)* She stands at a mic, sheet in hand, focused and a little nervous, mouthing through warmups. VOICEOVER (CHASE): "Every note mattered — you never knew who was listening." 3. *(~3s, practice room, handheld, mirror wall)* She's mid-motion rehearsing choreography, sweat forming, repeating a step over and over. VOICEOVER (CHASE): "I must have run that same eight-count a hundred times." 4. *(~3s, practice room, macro insert)* Close-up on her feet repeating the same step, breathing audible, tape blur softening the motion. No narration — ambient practice room sound only. 5. *(~3s, evaluation room, wide-to-close, tense finish)* She stands nervously in front of unseen evaluators, hands clasped, taking a steadying breath before the camera holds on her face. VOICEOVER (CHASE): "That was the version of me that started all of this."
- Camera flaws are itemised — delayed focus pulls, clumsy zooms, cut-off faces — which is exactly what self-shot footage looks like.
- Saying the camcorder never appears on screen resolves the logical trap of a POV shot of yourself.
- Lighting is allowed to change per location, so the piece reads as one real day rather than a lit set.
Japanese Strawberry Farm Selfie Vlog
A smartphone selfie vlog at a Japanese strawberry farm where the speaker delivers her lines naturally in Japanese.
A photorealistic smartphone selfie vlog that looks exactly like a real mobile phone recording. A young Korean woman (image = her face and hair) visits a beautiful strawberry farm in Japan on a sunny spring morning. She naturally speaks Japanese throughout the vlog. Holding her phone in selfie mode with realistic handheld movement, slight hand shake, authentic smartphone autofocus, and true-to-life colors, she smiles and says, 「今日はイチゴ狩りに来ました！」 ("Today I came strawberry picking!"). She walks through long rows of strawberry plants, carefully picks ripe red strawberries, and places them into a small woven basket. She chooses one fresh strawberry, takes a bite, smiles with genuine delight, and says, 「甘くておいしい！」 ("It's so sweet and delicious!"). As she continues picking, the basket gradually fills with strawberries. She proudly holds the full basket toward the camera, laughs naturally, then gives a warm wave and says, 「またね！」 ("See you!"), reaching toward the phone to end the recording. The video should feel exactly like a genuine smartphone vlog with natural human movement, consistent facial features, realistic strawberry picking, authentic outdoor lighting, no beauty filters, no CGI, no AI-plastic appearance, no subtitles, no logos, no watermark, and no background music—only real farm ambience, birds, gentle wind, footsteps, and natural outdoor sounds.
- The spoken line is written out in Japanese with a translation, so pronunciation and lip-sync have an exact target.
- Smartphone behaviour is described mechanically — handheld shake, autofocus hunting — rather than as a phone aesthetic.
- One location and one speaker keep the whole clip inside what a selfie vlog can plausibly show.
Coffee Prep Camcorder ASMR Vlog
A cozy self-shot camcorder vlog of making morning coffee, carried by grinder, pour and cup sounds rather than dialogue.
CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bright kitchen morning light. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic. STYLE: Cozy coffee-prep vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments. Focus on satisfying sounds: bean grinder whirring, portafilter tamping, steam wand hissing, cup clinking, milk frothing. SUBJECT: Young man in his mid-20s, plain t-shirt, hair slightly tousled, minimal accessories. Calm, focused energy while making his morning coffee. SETTING: Small kitchen counter with an espresso machine on a bright morning. Natural daylight, coffee beans and a mug nearby, quiet atmosphere. STORYBOARD: → (3s, propped medium shot) Places camera on the counter, switches on the machine. "Morning coffee, the proper way." → (3s, overhead shot) Grinds fresh coffee beans, fine grounds falling into the portafilter. → (3s, close-up) Tamps the grounds down firmly and evenly. → (3s, handheld shot) Locks the portafilter into the machine. "Here we go." → (3s, detail shot) Espresso streams slowly into a small cup. No dialogue. → (3s, medium shot) Pours cold milk into a small steel pitcher. "Time for the milk." → (3s, macro shot) Steam wand hissing as it froths the milk. → (3s, propped shot) Pours frothed milk carefully over the espresso, forming light layers. → (3s, warm ending shot) Holds the finished cup, takes a small sip, satisfied smile. "That's exactly what I needed." → (3s, final shot) Reaches toward camera, still holding the cup. "See you later." Hand covers lens as recording ends. AUDIO NOTES: Natural kitchen ambience — grinder whirring, tamping, steam hissing, milk pouring should be clearly audible. Dialogue quiet and casual. REALISM NOTES: Authentic body language, natural blinking, genuine focused smiles, occasional careful pauses while pouring, imperfect framing, focus breathing, bright morning light shifts. Should resemble a genuine personal coffee vlog on a consumer camcorder, not a commercial or AI-generated production. #Seedance #AIVideo #AIAnimation #GenerativeAI #AIArtCommunity #DreaminaSeedance25 #DreaminaAI #Seedance25 #Seedance #VLOG #Higgsfield @dreamina_ai @noman23761 @Strength04_X https://t.co/48xdJRUgB5
- Kitchen morning light is named as the exposure driver, so the auto-exposure shifts feel motivated.
- Minimal dialogue is stated as a style choice, leaving the sound design room to be the subject.
- Consumer camcorder artefacts are requested as a package, which is what separates this from a polished ad.
Trojan War Selfie Vlog
A woman films an ironic selfie vlog while the Trojan War rages behind her, until the danger finally breaks her composure.
Scene and Mood: A modern, camera ready woman films a casual selfie style vlog update while the Trojan War rages in full chaos behind her, her ironic commentary colliding harder and harder against real explosions, smoke, and clashing soldiers until the danger finally cracks her calm. Frame Map: Shot 1 (0 to 6s), extended arm selfie framing, her face and shoulders fill the left two thirds of frame, x=40%, foreground, chest up. Right third and background hold the smoking battlefield, distant soldiers clashing, burning siege structures. Shot 2 (6 to 14s), same selfie framing, camera whip shakes as a nearby impact throws dust into frame, her face still anchored left center. Shot 3 (14 to 22s), slightly wider selfie angle, x=45%, more of the background battlefield visible behind her right shoulder, chariots cutting across the midground. Shot 4 (22 to 30s), tight selfie close up, x=50%, face fills 70% of frame height, background reduced to a soft focus wash of firelight and smoke. Subject Lock: Long dark wavy hair, olive skin, sharp contoured features, gold hoop earrings, a dust smudged white linen wrap top, holding a matte black phone at arms length toward her own face throughout. Body angled three quarter toward the lens, weight shifting between feet as the ground shakes. Expression starts polished and bright for camera, cracks into wide eyed reaction at the nearby impact, recovers into a knowing smirk by the close. Free hand touches her hair or braces on nothing as she
- The joke is structural: foreground calm and background catastrophe are assigned to fixed frame regions.
- Frame coordinates keep her face on one side and the battle on the other, so both stay readable.
- The composure crack is scheduled as a beat, giving the comedy an ending instead of a loop.
Late-2000s Flip-Camera Coconut Vlog
A 30-second late-2000s flip-camera vacation vlog: an Indonesian creator hunts fresh coconuts through a village, with era-accurate camera flaws and ambient sound only.
Preserve the exact face, hairstyle, identity, skin tone, and body proportions from @ image1 throughout. Outfit: oversized terracotta linen shirt, dusty burgundy wide-leg trousers, brown leather sandals, small gold hoop earrings, loose natural wavy hair. Authentic Indonesian woman. Late-2000s personal vlog aesthetic. Extremely raw handheld flip-camera footage with heavy camera shake, natural reframing, partial face crops, focus hunting, exposure shifts, warm faded colors, mild digital noise, and authentic home-video imperfections. No posing, no cinematic glamour, no stabilization, no modern color grading. 00:00–00:04 Walking through a peaceful tropical village lined with coconut trees, smiling into the camera. "Today we're hunting for fresh coconuts!" 00:04–00:08 Stops at a small roadside coconut stall where a friendly local vendor expertly chops open a fresh green coconut. She watches with an excited reaction. 00:08–00:12 Takes her first sip of fresh coconut water, smiles brightly, and says, "This is so refreshing!" 00:12–00:16 Sits with local villagers on a wooden bench, chatting, laughing, and enjoying the relaxed atmosphere while holding the coconut. 00:16–00:20 Tries opening another coconut herself using simple tools, struggles playfully, laughs, and the locals cheer and laugh with her. 00:20–00:24 Scoops out the soft coconut flesh with a spoon, tastes it, and gives a happy thumbs-up to the camera. 00:24–00:27 Walks slowly through the village, waving to children and locals while carrying the empty coconut shell. 00:27–00:30 Stops beneath tall coconut trees, turns back toward the camera with a warm smile, waves, and says, "See you in my next adventure. Bye!" before naturally ending the recording. Natural ambience only: birds, palm leaves rustling, village conversations, coconut chopping sounds, footsteps, breeze, insects, and distant laughter. No background music, subtitles, logos, or watermarks. The footage should feel exactly like a genuine late-2000s handheld flip-camera vacation vlog with authentic human movement and realistic interactions.
- The era is expressed as concrete defects — heavy shake, partial face crops, focus hunting, faded warm colors — instead of a vague retro label.
- Eight timed beats each carry exactly one activity, so a full village visit fits 30 seconds without rushing.
- The audio brief is all diegetic ambience (chopping, birds, laughter) with music banned, which completes the home-video illusion.
Flower-Pressing ASMR Camcorder Vlog
A cozy flower-pressing vlog written as CAMERA / STYLE / SUBJECT / SETTING / STORYBOARD / AUDIO modules, with mini-DV imperfections and ASMR sound design.
CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bright natural daylight. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic. STYLE: Cozy flower-pressing vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments. Focus on satisfying sounds: petals rustling, paper pages turning, book weight settling, tweezers picking up petals, gentle smoothing. SUBJECT: Young woman in her early 20s, plain linen dress, hair loose, minimal jewelry, no visible logos or branded items. Calm, gentle energy while preserving flowers. SETTING: Small table near a window on a bright afternoon. Soft daylight, a plain heavy book, freshly picked flowers laid out, no visible brand names or packaging in frame. STORYBOARD: → (3s, propped medium shot) Places camera on the table, lays out a few fresh flowers. "Pressing some flowers today." → (3s, overhead shot) Arranges petals flat between two sheets of plain paper. → (3s, close-up) Uses tweezers to gently position a delicate petal. → (3s, handheld shot) Closes the paper carefully over the flowers. "Just need to keep them flat." → (3s, detail shot) Places the paper between the pages of a heavy book. No dialogue. → (3s, medium shot) Stacks a few more books on top for weight. "That should do it." → (3s, macro shot) A previously pressed flower being lifted out, delicate and flat. → (3s, propped shot) Arranges the pressed flowers onto a small card. → (3s, warm ending shot) Admires the finished arrangement, soft smile. "So delicate and pretty." → (5s, final shot) Sets the card on the windowsill, reaches toward camera. "See you next batch." Hand covers lens as recording ends. AUDIO NOTES: Natural ambience — petals rustling, paper turning, book settling should be clearly audible. Dialogue quiet and casual. REALISM NOTES: Authentic body language, natural blinking, genuine soft smiles, occasional gentle pauses, imperfect framing, focus breathing, bright daylight shifts. No copyrighted characters, logos, brand names, or recognizable public figures anywhere in frame. Fully original personal vlog content, not AI-generated or commercial in style.
- Each production concern lives in its own module, so you can swap the subject or the camera without rewriting the storyboard.
- Realism is requested as visible camcorder defects — focus hunting, auto-exposure shifts, imperfect framing — not as an abstract adjective.
- The named sounds (petals, paper, book weight, tweezers) map one-to-one onto storyboard actions, which is what makes the ASMR land.
Organic Grocery UGC Shopping Vlog
A vertical smartphone shopping vlog through a premium organic grocery store — selfie intro, product pickups, cart POV and a checkout ending.
A realistic UGC-style from lifestyle grocery shopping vlog filmed vertically on a smartphone with natural handheld movement and subtle camera shake. The video opens with the young woman entering a modern premium organic grocery store with warm ambient lighting, clean wooden shelves, fresh produce, and a bright minimalist interior. She holds the phone in selfie mode, smiles naturally, and gestures for viewers to follow her. She walks toward the refrigerated drinks section, scans the shelves, and picks up a green cold-pressed juice bottle, turning it slowly so the label faces the camera. Cut to a cinematic close-up as she twists the cap open and takes a refreshing sip beside a large sunlit window, smiling with a satisfied expression. Transition to a POV shot from inside a shopping cart as she pushes it through wide grocery aisles, occasionally looking down into the cart and smiling. Follow with an over-the-shoulder walking shot through beautifully organized shelves filled with premium groceries. Close-up of her hand selecting fresh oranges, gently inspecting one before placing it into the cart. End with a close-up of her picking up a vibrant dragon fruit, rotating it naturally in her hand while admiring its color before placing it into the cart. Finish with her walking toward the checkout while smiling at the camera, pushing the cart under warm golden lighting. Ultra-realistic, authentic creator content, premium grocery aesthetic, natural body language, realistic facial expressions, soft cinematic lighting, shallow depth of field, smooth transitions, realistic store ambience, subtle background music, 4K HDR, 24fps, clean color grading, lifestyle commercial quality.
- The shot flow alternates selfie, close-up and cart-POV angles, which gives an editor-style rhythm to a single-location vlog.
- Products are handled with specific gestures (rotating the label to camera, inspecting an orange) that read as habitual creator behavior.
- The store itself is art-directed — warm light, wooden shelves, minimalist interior — so the lifestyle tone comes from the set, not a filter.
Staged Paparazzi Tabloid Footage
Deliberately terrible long-lens tabloid footage of a fictional celebrity on a private beach — pixelation, panicked reframing and whispered operator lines.
Extremely low-quality amateur tabloid footage from a staged paparazzi-style shoot. Filmed from very far away with an old handheld consumer camcorder and cheap digital zoom. Severe pixelation, blocky compression, unstable autofocus, harsh overexposure, rolling shutter, dirty lens, shaky framing, accidental zoom jumps, clipped wind audio and muffled distant voices. Bright tropical afternoon. No cinematic polish. One fictional adult female entertainment celebrity, glamorous and confident, wearing a fashionable two-piece swim outfit with a minimal-cut bikini bottom, sunglasses and wet hair. Natural adult proportions, non-explicit presentation. One distant adult male companion in light resort clothing. Both are consenting performers in a staged scene. No resemblance to real public figures. Secluded luxury beach beside a private coastal villa, pale sand, turquoise water, palm trees, white cabanas, sun loungers and a small yacht offshore. Camera partially hidden behind rocks and tropical leaves. Deliberately poor amateur quality, authentic long-distance compression, unstable focus, realistic tropical wind, imperfect framing, staged consent, fictional adults, no nudity, no logos, no readable text, no recognizable celebrity likeness. 0-5s: Very shaky extreme-long shot - The camera searches across the beach through leaves, loses focus repeatedly, then finds the woman walking barefoot near the shoreline. The operator whispers in English: “Wait… zoom in. Is that really her?” 5-10s: Aggressive unstable digital zoom - She adjusts her sunglasses, laughs with the distant man and walks toward a white cabana. The image breaks into large pixels and the framing repeatedly cuts off their heads. 10-15s: Obstructed handheld shot - She turns slightly toward the ocean, wraps a light beach shirt around her shoulders, then suddenly looks toward the camera position. The operator whispers: “Oh no… she saw us.” 15-20s: Panicked reframing - The camera drops toward the sand, showing only rocks and blurred palm leaves. It rises again for one second: she is looking toward the lens and gives a knowing wave. A security golf cart enters the distant background. The operator says: “We’re leaving.” Abrupt corrupted-video cut to black.
- Low quality is the art direction: pixelation, blocky compression and accidental zoom jumps are all requested as features.
- The whispering camera operator adds a second character without ever entering frame.
- Careful guardrails (fictional adults, staged consent, no real likeness) keep a tabloid premise clean and usable.
Product Ads & Brand
Keep packaging, proportions, and label text stable while you direct the edit rhythm.
Sunglasses Unboxing Identity Ad
A UGC-style creator review that locks both the presenter and the sunglasses (box, case, frame, hinges) to references while she unboxes and reviews on camera.
Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, makeup, skin tone, body proportions, white sleeveless fitted top, light blue wide-leg jeans, pearl choker, rings, and bracelets consistently throughout the video. Use the uploaded sunglasses, retail box, and leather carrying case as locked product references. Maintain perfect product consistency, including the frame shape, lenses, hinges, colors, materials, and proportions. Create an ultra-realistic UGC luxury creator review filmed inside a modern luxury bedroom with warm golden-hour sunlight, soft natural shadows, and a premium lifestyle aesthetic. The camera feels like a handheld smartphone with subtle natural movement while maintaining cinematic commercial quality. The video begins with the woman sitting on the bed beside the retail box and leather case. Smiling at the camera, she says, "I genuinely wasn't expecting to love these this much." She picks up the box, opens it naturally, reveals the leather case, then slowly removes the sunglasses while continuing, "The packaging already feels incredibly premium." She rotates the sunglasses slowly in front of the camera, showing the frame, hinges, and lenses as natural reflections glide across the surface. She smiles and says, "The finish feels amazing, and they're incredibly lightweight." She puts on the sunglasses, stands up, and walks toward a large full-length mirror. Looking at her reflection, she adjusts the frame naturally and says, "Honestly... they look so good, and they're really comfortable on the eyes, even in bright sunlight." She turns slightly left and right so the sunglasses catch the sunlight from different angles before removing them with a smile. Walking back to the bed, she places the sunglasses beside the leather case and retail box, then picks them up one last time and holds them beside her face. Looking directly into the camera, she smiles warmly and says, "Definitely one of my favorite accessories this year." The camera slowly pushes in on the sunglasses before fading out. Ultra-realistic UGC fashion content, authentic creator review, cinematic handheld smartphone movement, luxury bedroom, macro product cinematography, realistic reflections, detailed frame textures, expressive facial animation, perfect lip sync, shallow depth of field, premium color grading, 4K HDR, 16:9, no subtitles, no logos, no watermarks, no on-screen text.
- Character and product get separate locked references with explicit attribute lists, which is what keeps a branded item from warping mid-video.
- Every spoken line is short and tied to a physical action — opening, rotating, trying on — so lip-sync has clear anchors.
- The mirror walk gives the product a second lighting environment without changing the scene, a cheap way to add coverage.
Presenter + product lockedReview lines tied to actionsTop-50 engagement on X
Gym Bench Phone Recording
A 30-second “phone left on a bench” gym recording: recovery, a hard cable set with trembling final reps, and a quiet spoken ending.
FORMAT: 30-second horizontal 16:9 realistic smartphone video. Create an authentic, imperfect everyday gym phone recording, as if a friend casually left a phone recording on a nearby bench. Use a standard smartphone camera with mild autofocus hunting, subtle exposure shifts, natural motion blur, compression artifacts, and slightly uneven handheld framing. No polished commercial look. 00–05s — ARRIVAL The character walks into a nearly empty gym after finishing a difficult set. They place a water bottle and towel beside a bench, sit down heavily, and lean forward with both elbows on their knees. Their breathing is noticeably heavy. Camera remains several feet away at a slightly low angle, as if casually recording from a phone placed on a gym bench. 05–10s — RECOVERY They slowly unscrew the water bottle, take two small drinks, then pause with the bottle still in their hand. Their chest continues rising and falling from exertion. They look down at their hands for a moment, flex their fingers, then wipe sweat from their forehead with the towel. 10–15s — THE NEXT SET A gym timer or workout screen is visible in the background but remains completely out of focus and unreadable. The character notices the timer, looks at it, gives a small tired smile, and shakes their head as if realizing they have less rest time than expected. They stand up slowly and roll their shoulders. 15–20s — PUSHING THROUGH They walk toward a cable machine and adjust the weight themselves. Close natural phone framing as they step into position. They briefly close their eyes, take one deep breath, then begin a controlled exercise set. Show realistic physical effort: tightening muscles, sweat collecting around the forehead and neck, slight trembling near the end of each repetition, natural breathing rather than exaggerated acting. 20–25s — FINAL REP The final repetitions become visibly difficult. They pause halfway through one repetition, breathe hard, regain control, and complete the movement with genuine effort. After finishing, they slowly release the handle, bend forward slightly, and place their hands on their thighs while catching their breath. 25–30s — QUIET ENDING They grab the towel, wipe their face and neck, then look directly toward the phone for a brief moment. With a tired but satisfied expression, they quietly say in a natural low voice: “Okay… that was worth it.” They pick up the water bottle and walk out of frame. End naturally while the camera continues recording for a moment before the clip stops. AUDIO Natural gym ambience only: distant weights being placed down, cable machine sounds, rubber flooring footsteps, ventilation hum, subtle clothing movement, water bottle clicks, realistic breathing, and occasional muffled gym sounds. Dialogue should sound spontaneous and slightly breathless, not scripted or theatrical. VISUAL REALISM Authentic smartphone footage, ordinary gym lighting, realistic skin texture, visible pores, natural sweat, slightly flushed face, damp hair around the forehead, realistic muscle movement, imperfect exposure, mild phone-camera sharpening, compression noise, subtle autofocus changes, believable shadows and reflections. STRICTLY AVOID: cinematic color grading, beauty filters, artificial skin smoothing, dramatic slow motion, music, subtitles, captions, logos, readable text, fake gym equipment, exaggerated muscles, perfect lighting, fisheye distortion, excessive camera shake, unrealistic sweat, duplicated limbs, warped hands, unnatural facial expressions, scene cuts, time jumps, or skipping the described actions.
- The camera is a character with a fixed premise — a casually placed phone — which locks framing, angle and imperfections at once.
- Effort is written as observable physiology: heavy breathing, sweat, slight trembling near the end of each rep.
- The unreadable background timer is a smart negative constraint — it adds gym realism without risking generated text.
Phone-on-bench premiseReal fatigue progressionUnreadable background timer
Chiropractic Clinic Social Video
A 30-second clinic social spot with realistic anatomy, believable physical contact and no text or logos anywhere in frame.
Create a 30 second 16:9 cinematic social video set inside a modern chiropractic and mobility clinic during late morning. The room has pale warm walls, clean wood flooring, black padded treatment tables, gray visitor chairs, a few green plants, subtle wall art, and tall windows overlooking leafy trees. Use natural daylight mixed with soft ceiling light, realistic skin texture, true fabric behavior, accurate anatomy, physically believable contact, consistent faces, and natural micro expressions. No text, no logos, no watermarks, no surreal motion. From 0 to 4 seconds, open on a wide establishing shot with a slow handheld push through the clinic. A calm male practitioner in a charcoal shirt guides an adult male client in a white shirt toward a treatment table. Other staff move softly in the distant background. The mood feels professional, relaxed, and observational. From 4 to 8 seconds, cut to a medium seated shot. The client sits centered while the practitioner stands behind him, gently checking shoulder level and neck rotation. Use small natural camera drift, shallow depth of field, window light on one side of the face, and realistic eye contact. Show quiet anticipation without exaggerated acting. From 8 to 12 seconds, move into a close side angle as the practitioner carefully positions the head for a controlled neck release. Keep the motion restrained and anatomically correct. Capture a quick release, a subtle facial reaction, a sharp breath, and an immediate smile. Let the camera react with a tiny authentic handheld movement rather than a dramatic shake. From 12 to 17 seconds, cut to a medium wide side view of the client lying on his side on the table. The practitioner braces the shoulder and pelvis, pauses, then performs one compact lumbar adjustment. Show realistic weight transfer, table cushion compression, shirt folds, breathing, hand pressure, and a brief surprised laugh from the client. From 17 to 22 seconds, cut to the client lying face down. The practitioner palpates the upper back, stacks both hands, and applies one controlled thoracic compression. Use a slightly lower camera angle, soft reflections on the table, gentle background activity, and a brief focus pull from the hands to the client’s relieved expression. From 22 to 26 seconds, transition to a head of table view. The client lies on his back while the practitioner places a black traction strap beneath the base of the skull. Build tension slowly and safely, then deliver one short controlled pull. The client reacts with wide eyes, then laughs and covers his face for a moment. From 26 to 30 seconds, finish with the client sitting upright, rolling his shoulders and turning his neck comfortably while the practitioner stands beside him. End on an honest shared smile and a slow pullback that reveals the bright clinic. Keep the final moment calm and satisfying, not promotional. Audio should feel captured on location with soft room ambience, distant clinic movement, clothing rustle, table creaks, natural breathing, quiet conversation without clearly audible words, and crisp but not exaggerated adjustment sounds. Add a low volume modern instrumental track with warm piano, soft bass, light percussion, and a gentle rise at each release, ending on a clean resolved note.
- The room is specified as a materials list — pale walls, wood floor, padded tables — so the space looks specified rather than generic.
- Asking for physically believable contact is what keeps hands-on treatment shots from looking wrong.
- Banning text and logos up front makes the footage usable as a brand plate later.
2 people in contactRealistic anatomyNo stray text or logos
Floating Sticker Outfit-Swap Reel
A vertical outfit-swap reel where four cut-out looks float around the frame like stickers and fly in on the beat to replace what she wears.
参考上传图片中的女主形象、脸型、五官、肤色、黑长发发型、身材比例和整体画面布局，生成一段8秒、9:16竖屏的甜酷风高机位卡点换装视频。 【人物与画面】 中央女主保持上传图片中的脸型、五官、肤色、黑长发和整体甜酷气质完全一致。 初始造型使用中央穿搭：运动装（短袖运动T恤 + 高腰运动短裤/短裙 + 运动鞋）。 画面四周固定悬浮4个小型穿搭人物，保持图片中的位置、比例、服装和朝向： 左上：吊带装 右上：牛仔装 左侧中部：古风装 左下：运动装变体 四个小人物都是完整人物抠像，外沿有清楚的白色虚线描边，像悬浮贴纸。 【场景与机位】 浅灰白色无影棚，背景干净，光线柔和通透。 摄影机固定在女主前上方，采用近距离高机位俯拍（约向下30度）。 女主自然抬眼看向镜头，头部和上半身更靠近镜头。 全程固定机位，不推拉、不摇镜、不旋转、不变焦。 【换装机制与时间线】 0.00–1.80秒：女主穿运动装，身体微微前倾靠近镜头，动作轻快自然，带甜酷表情。鼠标点击左上人物，左上吊带装人物飞向中央并放大重合，完成第一次换装成吊带装，动作连续不中断。 1.80–3.60秒：女主穿吊带装，一只手轻撩头发，身体轻微侧转。鼠标点击右上人物，牛仔装人物飞向中央并放大重合，切换成牛仔装，继续原有动作节奏。 3.60–5.50秒：女主穿牛仔装，双手自然摆动或调整衣领，身体轻微下沉再起来。鼠标点击左侧中部人物，古风装人物飞向中央并放大重合，切换成古风装，动作保持连贯。 5.50–8.00秒：女主穿古风装，缓缓转回正面，衣摆自然垂落，抬眼直视镜头，以甜酷又带一点清冷的姿势结束。 【声音】 无背景音乐。保留鼠标点击声、人物飞入的短促音效、换装卡点音效，可轻微加入衣料摩擦声。 【强制约束】 - 换装前后必须保持同一张脸、同一发型、同一身材比例 - 动作方向、重心、手臂位置必须连续，不能卡顿或僵硬 - 四个描边小人物全程固定在原位置，点击后原人物不消失 - 换装必须由完整人物抠像飞入、放大、重合完成 - 不要生成矩形缩略图、人物残影、双重人物、服装叠穿、肢体畸形 - 古风服装的袖子和裙摆要有自然垂坠感，不能僵硬漂浮 - 人脸清晰不变形，皮肤质感真实，画面稳定 三、生成后微调建议 如果某一秒衣服不准，就把对应服装的描述写得更具体再重新生成。 想更丝滑可以在每个换装节点加遮挡动作（甩发、捂脸、转身）。 这个方法目前稳定性和出片效率都很高，特别适合女装电商和穿搭账号批量出内容。 需要其他风格（JK、职场、纯古风等）也可以。
- The floating cut-outs are specified with white dashed outlines and fixed positions, so they behave like UI rather than characters.
- A locked high camera angle with no push, pan or zoom keeps the swap mechanic perfectly legible.
- Each swap is pinned to a timecode, which is what makes the changes land on beat.
Sticker-style outfit swap4 looks fly in on beatVertical reel
Crystal Ball Match-Cut Montage
A beat-synced match-cut montage that keeps a flawless crystal ball locked in focus while eight worlds flash by behind it.
A fast-paced, cinematic match-cut short synced to a driving electronic beat. A flawless crystal ball stays fixed dead-center the entire time, with a glowing 'seedance' logo etched inside it. The crystal ball stays in razor-sharp focus while, on every powerful drum hit, the background switches seamlessly at high speed: Scene 1: Macro close-up, cinematic water splashing around the crystal ball, refracting intricate light and shadow. Scene 2: A vintage morning cafe, the crystal ball resting on a raw-wood tabletop, with rising coffee steam and a blurred stream of commuters out the window behind it. Scene 3: Golden hour at dusk, a skateboarding youth tossing and catching the crystal ball one-handed, against a fast-receding streetscape and gorgeous backlit sunset. Scene 4: A frenzied music festival, hands raised high holding the crystal ball, refracting the dazzling stage lasers behind it. Scene 5: A lively family party table, the crystal ball resting at the center, with blurred figures toasting and reaching for food in the background. Scene 6: A dim movie theater, hands cupping the crystal ball as the faint glow of the huge screen flows across its surface. Scene 7: The crystal ball on a violently vibrating speaker membrane, seamlessly cutting at the music's climax to the spinning center of a DJ turntable. Scene 8: A night of outdoor camping, the background becoming a warm bonfire and the swaying bokeh of string lights. Toss finale: On the final accent of the music, the crystal ball is thrown high out of the top of frame; an instant cut to a pure black background, where a minimalist white-on-black 'seedance' appears dead-center. Cut tightly to the rhythm of the energetic BGM (beat-synced transitions), top-tier cinematic color grading. Photoreal glass refraction and transmission material, complex ray tracing, global illumination. The subject is razor-sharp while the background carries strong motion blur for maximum visual impact.
- A single locked focal subject across all eight scenes gives the editor a natural anchor for clean match cuts.
- Every background change is pinned to a drum hit, so the montage feels musically driven rather than random.
- Photoreal glass refraction plus heavy background motion blur makes the high-speed cutting read as premium, not chaotic.
Brand Concept Window Reveal
A cinematic brand short that rushes past windows of every kind, ending in a human eye that opens onto the seedance logo.
A cinematic brand-concept short. [reference image 1] is the opening frame: the image trembles slightly as the camera slowly pushes in toward tree shadows rushing past outside the window; the shadows recede faster and faster, then suddenly cut to [reference image 2], where the speed abruptly slows and the camera drifts gently forward along a stream, full of birdsong and blossoms. The camera moves down, going underwater, with the sound of bubbles; a school of orange jellyfish drifts gracefully past the lens [reference image 3]. The camera slowly pulls back, a school of small fish flickers past and swims from the water through into the window [reference image 4], where a young girl looks left and right, watching the little fish. The camera slowly pulls back, the image goes out of focus, then refocuses and sharpens, switching in time with the music: a Chinese-garden lattice window [reference image 5] with light spinning through it, a stained-glass church window, an airplane porthole, a domed skylight, a bay window, venetian blinds, a European dormer window, a peephole in a door, a camera viewfinder, a bird's eye, and a macro close-up of a human eye. The image holds on the human eye close-up, then the eye closes, the screen goes black, and the eye suddenly opens again, with 'seedance' appearing at the center of the eye on a strong accent.
- A single recurring motif (windows) gives a rapid montage a clear conceptual through-line.
- Tempo shifts between rushing and slowing keep the edit dynamic and prevent monotony.
- Reference frames lock in the key visual beats so the transitions stay on-brand and consistent.
Dreamy Fashion Beauty Film
A 24-second haute-couture beauty film built on dreamy bokeh, silky motion-blur transitions, volumetric light, and hyper-real materials.
[Overall style] A 24-second haute-couture, brand-grade visual film with an intensely cinematic, high-end texture. The image emphasizes dreamy bokeh, silky motion-blur transitions, volumetric lighting, and hyper-real material detail. [Shot breakdown] [0-5s]: Dreamy prologue and macro close-up. An extremely high-quality macro close-up. A slender hand reaches into the air, fingertips touching star-bright, shimmering colorful bokeh. As the light flows, a seamless silky transition leads to an elegant woman in a pure-white sheer gown, entranced as she plays a vintage piano. Shallow depth of field, the background blurred into a beautiful teal palette. [5-15s]: Then cut into a fluid follow shot: a woman in a French wide-brimmed straw hat and flowing white dress runs lightly through a dense flower path full of pink-orange roses and blue hydrangeas. Light filters through the leaves casting dappled shadows, perfectly showing the soft breeze, the realistic physics of the fluttering skirt fabric, and the hyper-real texture of the petals. [15-24s]: Serene aesthetics and light refraction. The pacing slows into an exquisitely beautiful slow-motion. A girl sits at a black wrought-iron table beside a European vintage gilded fountain, quietly reading. Crystal-clear soap bubbles float through the air, their surfaces perfectly refracting the surrounding flowers and warm sunlight. The moment water droplets splash is clearly visible, showcasing the model's top-tier rendering of transparent materials, water refraction, and complex lighting.
- Three escalating beats (macro, follow shot, slow motion) give the film a clear rhythmic arc.
- A consistent dreamy palette and bokeh language unify otherwise distinct scenes into one luxury aesthetic.
- Transparent materials like bubbles and water droplets are used deliberately to show off refraction rendering.
Floating Desert Museum
A cinematic art-ad shot that pushes through golden desert into a minimalist white museum floating above the dunes, then opens its walls to the sky.
Cinematic quality, high-end feel, a golden desert at dawn, a minimalist white art-museum building floating above the dunes, the building's surface carrying fine stone texture and soft reflections. Sunlight passes through the airborne sand to form volumetric light, with distinct layers of distant dunes. The camera starts on an ultra-wide desert panorama, slowly pushing forward, passing through the flying sand grains, into the interior of the floating building. Inside there are suspended sculptures, semi-transparent silk installations, and a character in a white robe, the fabric swaying naturally in the wind. The camera makes a smooth orbiting move around the character, and finally the building walls slowly open to reveal the vast sky and desert. High-end art-advertising style, realistic lighting, refined materials, cinematic composition, elegant motion, surreal yet believable.
- A single continuous push-in from wide desert to interior gives the surreal premise grounded spatial logic.
- Volumetric light through airborne sand makes the floating building read as physically lit and believable.
- The wall-opening reveal provides a clear, satisfying payoff that scales from intimate to vast.
Desert Fashion Brand Film
A 30-second high-fashion concept film of models against red dunes, breaking the fourth wall to reveal a giant LED virtual studio.
A 30-second high-end brand-concept short with intense visual tension. It opens on a surreal upside-down angle, the camera flipping with gravity to reveal a model's feet in vintage suede boots stepping lightly onto rolling crimson dunes, a macro close-up on the boots' brushed-suede nap and the rough red sand grains clinging to them. Then it cuts into a montage full of weightlessness and dreamlike color: young male and female models falling weightlessly backward amid surging amber sandstorm and cold rim light; the camera cuts swiftly into razor-sharp facial close-ups - wind-blown sand drifting across lashes dusted with tiny golden grains, models wearing vintage metal-framed sunglasses whose curved lenses clearly reflect the blazing wilderness sun and the storm. Then, fingers wearing heavy distressed silver rings gently brush across a rugged, weathered rock wall and wildly swaying reeds. The imagery makes heavy use of expressive camera language: through an extreme low-angle macro lens, shooting up through the blurred, crystalline edge of a natural mineral crystal at the deep vast starry sky and explorers freely passing through it. Amid the grand scenes, high-quality partial close-ups are densely interspersed: the texture of coarse linen shirts flapping in the wind, the model's taut, cold jawline, and the sheen of sweat shimmering on the neck skin in backlight. Combining a fisheye lens, fast rotating camera moves, and silky visual-misalignment transitions, it creates an avant-garde, wild, tension-filled mysterious dynamism. At the short's climax, the camera dramatically pulls back, breaking the fourth wall to reveal that this is in fact a high-end virtual studio built with a giant LED star-trail ring sky-screen and a real red-sand array, perfectly colliding the desolate vastness of the wild with the avant-garde industrial sense of a real set. At the end, the pacing slows and returns to delicate texture close-ups: a woman with loose hair leans against a vintage off-road vehicle, the camera slowly sweeping across the body's mottled, peeling heavy-metal paint as she casually lets fine sand slip through her fingers. Cold, bright moonlight side-light precisely outlines the rugged fabric pores of the distressed leather jacket, the cold reflections off the heavy-metal zippers, and the woman's cold, three-dimensional facial contours. The whole presents a vintage film-grade color aesthetic, deep night-blue interwoven with blazing mineral orange, the image expansive, free, full of high-quality brand tension. Finally, the word "seedance" elegantly emerges at the center of the frame.
- Macro texture close-ups intercut with epic scale create the editorial rhythm of a real fashion campaign.
- The fourth-wall LED-studio reveal adds a conceptual twist that recontextualizes everything before it.
- A disciplined night-blue and mineral-orange palette holds the wild montage together as one brand world.
Mechanical Flower Bloom
A one-take macro push from a metal bud into the precision gears inside, climaxing as a mechanical flower fully blooms and light radiates out.
The theme is "mechanical flower bloom". The image needs to highlight the generative video model's strengths in lighting and shadow, art detail, realism, camera movement, and cinematic character feel. The overall style is a high-end tech-brand ad with strong visual impact. The video uses a single-take macro push-in shot, starting from a metal flower bud in darkness, gradually entering the precision mechanical structure inside the petals, and finally climaxing on the image of the mechanical flower fully blooming with light radiating outward. It requires realistic physical lighting, refined metal and glass materials, delicate mechanical motion, stable composition, cinematic color grading, no subtitles.
- A single macro push-in turns a product reveal into one continuous, mesmerizing motion.
- Precise metal and glass materials with realistic lighting sell the premium tech-brand positioning.
- The bloom-with-light climax gives the short a clear, punchy payoff frame.
Silk Road Pomegranate Journey
A 30-second mineral-pigment flat animation tracing a pomegranate "from the land to the cup" along the ancient Silk Road.
Overall style: mineral-pigment flat animation, Oriental and Silk Road decorative aesthetics, mineral-pigment texture, cinnabar red, ochre, malachite green, ultramarine, with gold accents, paper and mural texture, flat layering, no real photography, no 3D realism. The pacing moves from still to motion, then back to stillness, highlighting the "from the land to the cup" sense of journey and abundance, with cheerful, Western-Regions-style music. Shot 1: A branch appears, an abundant opening (0-4s). Ochre and vermilion color blocks bleed across a Silk Road painted-paper surface; a pomegranate branch stretches out from the right side of the frame, the leaves heavy with distinct mineral-pigment layers. A plump pomegranate slowly appears on the branch, its shell red tinged with gold, the contour round and serene. Sunlight falls on the skin as golden discs and gold-leaf flecks, the pomegranate surface glowing warmly, like a fruit ripened by time - an opening that is abundant yet restrained. Shot 2: Gently picked, the journey begins (4-7s). The pomegranate is gently picked by a Western-Regions handmaiden, the movement steady and graceful. The background gradually reveals scrolling-grass patterns, ancient motifs, and a decorative long-scroll composition, hinting that it comes from a distant land. The frame transitions naturally from the static branch into an unfolding journey, mountains, roads, and towns beginning to spread flatly in the background, like a Silk Road scroll being slowly opened. Shot 3: Crossing the ancient road, over mountains and rivers (7-13s). A camel-caravan silhouette advances slowly, the bells shown as tiny gold dots marking rhythm, the pomegranate appearing in a camel's pack. The ancient road crosses dunes, oases, and city gates, wind and sand sweeping past as flowing patterns, gold-lined roads extending endlessly into the distance. The colors are rich and refined, like Silk Road murals fused with mineral-pigment illustration. The pomegranate stays vivid and plump throughout the long journey, as if preserving the sunlight, heat, and abundance of a distant land to this day. Shot 4: An ancient-to-modern transition, arriving in the present (13-16s). The ancient patterns and architectural outlines in the background gradually simplify, time quietly transitioning to a modern space. The pomegranate is placed on a modern counter, the table and vessels rendered in clean flat geometry, the ancient and modern visuals connected in the same frame, the pacing shifting from "long journey" to "arrival". Shot 5: Cutting open the pomegranate, the visual climax (16-20s). A hand gently cuts open the pomegranate, the movement slow and restrained, the instant the shell splits open full of ceremony. Shot 6: Pressed into juice, abundant flow (20-24s). The seeds enter a vessel and are pressed into rich pomegranate juice, the liquid flowing with a deep-red translucent quality and fine mineral-pigment grain. The juice is slowly poured into a modern glass, the glass outline clean and simple, the red liquid rising in the cup, its surface rippling with faint highlights. A few ice cubes drop in, the cool white forming a sharp contrast with the deep red, fine droplets forming on the glass wall, the refreshing feel maxed out. Shot 7: Modern drinking, the journey lands (24-27s). The background cuts to a modern life scene, window light, tabletop, fabric, and plants keeping a flat decorative quality and warm palette. The juice glass sits at the center, the ancient road, caravan, and city-gate patterns faintly layered around it, hinting that this glass of juice comes from a long journey. The mood is abundant, warm, and serene. Shot 8: Time converges, a poster-style close (27-30s). The ancient-road patterns and modern space in the background gradually merge, like time converging into this glass of juice. The frame briefly flashes back to the pomegranate on the branch, the caravan shadows on the ancient road, and the red seeds, completing the "from the land to the cup" loop. Finally it closes into an ad-poster composition: the deep, vivid pomegranate juice at the center, a split pomegranate beside the cup, ancient-road patterns, golden light points, and modern-life elements layered around, the image quiet yet full of life, like a journey across time and land finally arriving in the present, with the tagline "seedance, a gift from the Western Regions".
- A consistent mineral-pigment, flat-layered style gives the whole journey a distinctive, non-photoreal identity.
- The "from the land to the cup" through-line carries the pomegranate across eras with clear narrative logic.
- Ancient-to-modern transitions reward attention and build to a satisfying poster-style close.
Coffee Machine Tutorial
A 30-second step-by-step capsule-coffee-machine setup tutorial with labeled shots, voiceover, and reference frames for each part.
A 30-second capsule coffee machine installation and setup tutorial video. 0-2s, the opening title text reads: seedance capsule coffee machine installation and use tutorial 2-5s, Step 1: install the water tank, see [reference image 1] Shot: medium shot, slight high angle. Position: back of the machine body. Action: align the water tank with the slot on the back of the body, push it straight down until it clicks into place. Requirement: clearly show the alignment between the tank's bottom clip and the body's slot, the transparent part of the tank showing the water level line. Voiceover: "First, install the water tank." 5-9s, Step 2: install the drip tray, see [reference image 2] Shot: close-up, front view. Position: front of the bottom of the body. Action: push the drip tray parallel into the rails at the bottom of the body until it fully seats at the bottom. Requirement: show the rail-alignment process, highlighting the smoothness of the sliding-in action. Voiceover: "Next, align the tray with the bottom rails." 9-13s, Step 3: install the used-capsule collection box, see [reference image 3] Shot: close-up, slight low angle. Position: the cavity beneath the drip tray. Action: align the collection box with the recess and push it in, flush with the drip tray. Requirement: show how the collection box fits with the body, confirming it is seated correctly. Voiceover: "Then insert the capsule collection box." 13-18s, Step 4: first fill with water, see [reference image 4] Shot: close-up, side view. Position: top / back water tank of the body. Action: open the tank lid, pour in clean water up to the MAX water level line, close the tank lid. Requirement: highlight the water level marking, the water pouring in clearly visible. Voiceover: "Open the tank lid and pour in clean water. Be careful not to exceed the maximum water level line." The image highlights the maximum water level line. 18-25s, Step 5: power on, see [reference image 5] Shot: medium shot, front view. Position: front of the body. Action: plug in the power cord, press the power button, the indicator light changes from blinking to steady (preheating complete). Requirement: close-up of the power button and indicator-light state change, showing the process from waiting to ready. Voiceover: "Connect the power and press the power button." 25-30s, Step 6: first rinse (no capsule), see [reference image 6] Shot: medium to close-up, front-side view. Position: front of the body, cup under the spout. Action: without inserting a capsule, press the brew button directly, hot water flows out to rinse the lines, the water flows into the cup. Requirement: emphasize the "no capsule needed" prompt label, showing the whole rinse-water flow. Voiceover: "Last step, the first rinse. No capsule needed, just press the brew button. Your coffee machine is now ready to use."
- Explicit shot, position, action, and requirement per step give the model precise tutorial direction.
- Timed segments with voiceover keep the how-to clear and easy to follow.
- Reference frames for each part ensure the product stays consistent across all six steps.
Fruit Biscuit Product Ad
A bright, beat-driven fruit-biscuit ad with geometric arrays and a slow-motion snap that bursts the fruit filling.
Bright, colorful commercial-ad style, with fruit biscuits as the hero, featuring four flavors - strawberry, apple, grape, and orange - the strawberry flavor referencing [reference image 1]. The biscuits and their matching fruits are arranged in a strongly ordered geometric array, the overall image clean, high-end, and strongly rhythmic. The opening quickly establishes visual focus with fruit, referencing the composition of [reference video 1], the music's downbeat cutting in. Then the different-flavor biscuits line up neatly, cut to close-up, referencing the motion and camera moves of [reference video 2]. In the climax segment, a biscuit is snapped in half, instantly entering slow motion, the fruit filling bursting open, crumbs flying, the juicy feel and grain impact magnified and showcased, referencing the impact of [reference video 3]. A horizontal array forms a rhythmic parabolic toss, referencing the motion of [reference video 4], highlighting the orderly beauty and product richness. Then it quickly returns to fast-paced editing. At the end, the English text "One bite of crispness, a heart full of delight" cuts in rapidly word by word, paired with strongly rhythmic text motion and a product freeze, referencing [reference video 5], finally closing with a brand feel, the biscuits and fruit radiating outward, referencing [reference video 6], the image full of a young, energetic, delicious, share-worthy ad atmosphere.
- Geometric arrays plus beat-synced cuts give the food ad a clean, premium, rhythmic energy.
- The slow-motion snap that bursts the filling is a high-impact appetite hook.
- Multiple video references pin the composition, motion, and impact for a polished commercial feel.
Desert Lizard Grapefruit Ad
A 29-second 3D animated ad where a parched desert lizard finds a grapefruit that floods the desert into a juicy sea.
3D animation ad style, bright and translucent colors, the pulp and juice should have a strong refreshing, impactful feel. The overall vibe is like a high-quality commercial animation short, with a touch of exaggerated humor. The desert horned lizard character is cute, lively, and very expressive, see [reference image 1]. The image texture references the soft natural light, delicate fuzz / skin texture, dreamy macro depth of field, and that real-yet-playful feel in the reference image. 0-3s: The image is a desert scorched by the blazing sun. The air is so hot it distorts, the sand is scalding, the distance seems to smoke. A desert horned lizard lies on the burning sand, tongue lolling slightly, eyes glazed, almost dried out. It sways with every couple of steps, the whole lizard about to "evaporate". Sound: the whoosh of heat waves, slight exaggerated cracking sounds. 3-6s: The lizard suddenly stops, its nose twitching. It looks down and there, buried in the sand, is a cool, plump, dew-covered grapefruit. The grapefruit glitters in the sunlight, the skin delicate, like a miracle suddenly appearing in the desert. Performance: the lizard's eyes go wide in an instant, like spotting a lifeline. Sound: a "ding" discovery sound effect. 6-8s: The lizard makes a flying lunge, both hands clutching the grapefruit tightly, its whole face pressed against the rind. It shows a "finally alive again" blissful expression. The image freezes for 1 second, forming an exaggerated, funny ad memory point. Sound: a thud, then half a second of silence. 8-11s: The lizard grabs the grapefruit. The grapefruit rind splits open, the plump pulp inside glistening with translucent sheen. The next instant, the juice doesn't trickle out - it gushes out like a tsunami. Sound: a "crack" bite-open sound, followed by an exaggerated juice-bursting sound. 11-16s: Orange-pink, clear, glistening grapefruit juice gushes wildly, pouring down the dunes, quickly flooding the entire desert. The dry yellow sand instantly becomes a cool, shimmering, fruit-scented summer sea. The cacti, rocks, and small dunes in the desert are swallowed one by one by the juice waves, the image exaggerated and dreamy. Performance: the lizard is excited at first, then the next second realizes something's wrong, its expression turning from delight to terror. 16-20s: The lizard is nearly drowned by the "grapefruit sea", frantically clutching half a grapefruit like a life buoy, floating on the surface. It pokes its soaking head out, looking utterly dazed. The sea surface sparkles, the color like juice lit by the sun. Sound: exaggerated splashing, sea sounds, with a touch of comedy. 20-23s: The image suddenly cuts to a white screen. In the center appear the brand name and slogan: "Seedance Grapefruit, bite into the pulp, and summer pours out." Voiceover reads the whole line: "Seedance Grapefruit, bite into the pulp, and summer pours out." Sound: a clean, refreshing brand chime. 23-29s: The white screen cuts back. The lizard is now leisurely sitting on a floating grapefruit, wearing little sunglasses, holding a straw cup, drifting lazily on the "juice sea" on vacation. Around it float orange pulp, little ice cubes, and cool splashes, the sky turning azure, the mood shifting from "survival" to "vacation" in an instant. Finally the lizard leans contentedly against the grapefruit, the camera pulls back, freezing on a refreshing, bright, fun summer scene. Sound: relaxed summer music, gentle lapping waves. Subtitles can keep only the brand name, no need to add too much text.
- A clear comedic arc (survival to vacation) gives the product ad a memorable, shareable story.
- The juice-tsunami exaggeration turns a flavor claim into a spectacular visual hook.
- An expressive character referenced from an image keeps the cute, playful brand tone consistent.
Impossible Warrior Fashion Editorial
A high-fashion photoshoot staged on a burning battlefield, mixing luxury editorial posing with brutal fantasy action.
Use the provided image as the strict visual reference for the warrior’s face, blonde hair, armor, fur jacket, leather boots, sword, body proportions, ruined battlefield, burning fortress, smoke, embers, and dark cinematic atmosphere. Preserve her identity and outfit throughout the entire sequence. Create a 20-second impossible high-fashion warrior photoshoot, blending sensual confidence, brutal fantasy action, luxury editorial posing, explosive VFX, and aggressive cinematic camera work. The result must feel like a viral fashion campaign filmed in the middle of a medieval war. 0–4 seconds — Iconic opening pose Begin with the exact composition of the reference image. The warrior stands on shattered stone, sword lowered beside her, staring directly into the lens. Her hair and fur move violently in the wind while embers spiral around her. The camera rushes toward her with a low-angle dolly-in. A powerful white flash freezes her pose, followed by a horizontal blue lens flare crossing her eyes and armor. 4–8 seconds — Fashion meets combat She walks toward the camera with controlled, sensual confidence as explosions erupt behind her. Use rapid editorial cuts: close-up of her eyes, lips, hand tightening around the sword, fur texture, armored waist, boots crushing burning debris. She suddenly pivots and blocks an incoming blade from an unseen attacker. Sparks explode across the lens as the camera whip-pans around her. 8–12 seconds — Impossible action photoshoot She launches into a fast spinning sword movement, cutting through smoke and shattered banners. Freeze her mid-motion in a dramatic fashion pose as dozens of camera flashes fire from impossible angles. Add elegant motion echoes, metallic silhouette trails, floating reflective shards, streaking embers, and anamorphic lens flares. Each flash captures a different powerful pose before snapping back into live action. 12–16 seconds — Sensual hero moment The action suddenly slows. She plants the sword into the ground, steps close to the lens, and leans slightly forward with a fierce, provocative gaze. Wind sweeps her hair across her face while warm firelight shapes her silhouette. The camera performs a tight orbit around her body and rises into a close-up. A strong golden lens flare blooms behind her shoulder as ash drifts through the frame. 16–20 seconds — Epic viral finale A massive explosion destroys part of the fortress behind her. Without looking back, she pulls the sword free and turns sharply toward the camera. Use an extreme speed ramp as she swings the blade directly past the lens, creating a seamless transition into three rapid flash-frozen editorial poses: sword over her shoulder, blade pointed downward, then a dominant frontal stance. Finish on a slow-motion hero frame with the warrior standing perfectly centered, smoke and fire behind her, embers suspended in the air, her hair flowing, armor glowing along the edges, and a huge cinematic lens flare crossing the screen. Ultra-premium fantasy fashion editorial, sensual but powerful warrior energy, impossible battlefield photoshoot, luxury magazine attitude, brutal sword choreography, low-angle camera, macro beauty shots, whip-pans, fast orbit movement, snap zooms, speed ramps, flash photography, freeze frames, motion echoes, metallic VFX, realistic fire and debris, dramatic anamorphic lens flares, realistic hair and fabric physics, no dialogue, no text, no subtitles, no identity drift, no wardrobe change, no facial deformation, no extra limbs.
- The reference is scoped to cover both character and environment, so the battlefield stays as consistent as the outfit.
- Naming two opposing registers — luxury editorial and brutal fantasy — tells the model to hold both rather than pick one.
- Photoshoot framing justifies deliberate posing that would look artificial in a narrative scene.
Crimson Studio Noodle Commercial
A nine-cut editorial noodle commercial on a crimson backdrop — broth splash physics in slow motion, fashion poses and a sunglasses hero shot.
Style: Bold high-energy food commercial cinematography, 8K photorealistic, deep crimson-red studio backdrop, dramatic dynamic splash effects, glossy vibrant styling, fashion-editorial meets food-ad tone. 24fps, punchy fast-paced motion with slow-motion splash inserts, no jitter. Character: A stylish young woman with double-bun hairstyle adorned with colorful beaded accents and ribbons, red tinted sunglasses, bold red lipstick, wearing a blue-and-black dragon-print traditional-style dress with a wide black belt. Confident, playful, high-fashion attitude. Subject: A white ceramic bowl filled with rich reddish-brown broth, noodles, bok choy, lotus root slices, enoki mushrooms, and dumplings — dynamic splashing broth throughout. Setting: A deep red studio backdrop with golden fan props framing the scene. CUT 1 — Dynamic action shot, slow motion: She lifts chopsticks holding noodles high above the bowl, broth splashing dramatically upward with lotus root and bok choy suspended mid-air, confident smirk toward camera. CUT 2 — Medium shot, seated pose: She sits cross-legged holding the bowl, chopsticks lifting noodles toward her mouth, red sunglasses catching studio light. CUT 3 — Elegant seated pose, static hold: She leans back gracefully with legs crossed, bowl balanced in one hand, confident editorial gaze into camera. CUT 4 — Medium shot, presenting pose: She holds the bowl forward toward camera with both hands, steam rising gently, inviting confident expression. CUT 5 — Explosive splash shot, slow motion: Broth erupts upward in a dramatic arc as she reaches toward the bowl with chopsticks, lotus root and greens flying through the air in rich detail. CUT 6 — Extreme dynamic splash shot, slow motion: A massive eruption of broth, noodles, and vegetables cascades around her in full-body motion, chopsticks raised triumphantly, golden fans framing the chaos. CUT 7 — Action eating shot, slow motion: She lifts a large tangle of noodles from the steaming bowl with chopsticks, broth dripping and splashing at the edges, focused intense expression. CUT 8 — Extreme close-up, dramatic splash: Broth splashes upward around her face as she peers over lowered sunglasses with wide, playful surprise, mouth open mid-reaction. CUT 9 — Final hero shot, slow motion: She adjusts her sunglasses with one hand while broth splashes dynamically beside her, confident final pose against the deep red backdrop with golden fans in frame. Camera: Fast dynamic handheld-style energy on splash shots, smooth static holds on posed shots, high-speed capture for slow-motion splash details. Lighting: Bold saturated studio lighting, warm rim light on broth and steam, sharp contrast against the deep red backdrop. Color palette: Crimson red, warm amber broth tones, deep indigo-blue dress pattern, gold accents. Audio: Upbeat energetic instrumental with punchy percussion hits synced to splash moments, sizzling/broth-splash SFX, chopstick clicks, playful vocal ad-lib on the final reaction shot.
- The cut list alternates splash spectacle with composed poses, giving the ad a rhythm instead of nine identical explosions.
- Splash contents are itemized (lotus root, bok choy, noodles), so the debris reads as the actual dish.
- One styled character carries attitude through every cut, which keeps a product-first ad from feeling anonymous.
Cookie Split Macro Snack Ad
A ten-second macro snack ad cut second-by-second: cookies split, collide and orbit while molten chocolate stretches, snaps and splashes.
A cookie split apart at center frame explodes into flying halves as thick chocolate filling stretches between them in a taut glossy strand, camera whip-zooming out on impact with crumb debris blasting past the lens [00:00–00:01]; cut to the two halves flying apart and shattering into smaller pieces that scatter and tumble through a deep purple gradient void streaked with warm motion-blur light trails [00:01–00:02]; cut to a whole cookie rocketing toward camera trailing molten chocolate that whips and chases behind it like a ribbon [00:02–00:03]; cut to two cookie halves colliding head-on at center frame, chocolate filling smashing and fusing between them in a thick glossy bridge, crumbs flung outward on impact [00:03–00:04]; cut to a torn cookie snapping apart again in extreme close-up, filling stretching into thin threads before snapping free in slow motion [00:04–00:05]; hard cut to a whole cookie held suspended and slowly rotating inside a warm-lit vortex, crumbs and light streaks spiraling around it [00:05–00:06]; cut to a thick rope of chocolate drizzling downward in slow motion toward a bed of chocolate crumbs, a single droplet falling beside it [00:06–00:07]; cut to the chocolate strand landing and splashing across the crumb surface, sending a crown-shaped chocolate splash upward with fine droplets suspended at peak [00:07–00:08]; cut to the packaging orbiting into frame beside a whole cookie and a cracked half, both circling slowly inside a swirling motion-blur ring on a dark surface [00:08–00:09]; cut to a push-in on the packaging tilted beside a cookie half revealing the glossy filling, warm rim light catching the foil edges [00:09–00:10]; cut to the packaging tumbling into frame with cookies and loose crumbs scattering around it in an arc, settling at a dynamic
- Per-second cuts force one physical event each, which is the only way ten seconds can hold this much action legibly.
- Chocolate behavior is written as material states — taut strand, thin threads, crown splash — so the filling stays continuous, not generic goo.
- The packaging enters late and orbits with the product, integrating branding without pausing the motion.
Luxury Diamond Lightning Reveal
A short dark-luxury product reveal: a jewelry box opens, a gloved hand lifts the diamond, and electric-blue lightning forms around it as it floats.
Create a cinematic luxury diamond advertisement with a dark premium aesthetic. A black jewelry box slowly opens to reveal a flawless diamond. The camera pushes in for an extreme close-up as a gloved hand lifts the diamond. As it rises, electric-blue energy and realistic lightning begin forming around it. The diamond floats in the air while powerful lightning strikes in the background, with glowing particles, volumetric lighting, realistic reflections and physically accurate diamond refraction. Smooth cinematic camera movement, dramatic lighting, photorealistic CGI, premium commercial quality, realistic physics, highly detailed, consistent diamond throughout the entire shot.
- The reveal follows a familiar luxury-ad grammar (box, glove, lift, float), so the model has a strong prior to execute.
- “Physically accurate diamond refraction” targets the one optical property that makes gems read as real.
- A single escalating effect — building lightning — gives the ten seconds an arc without any dialogue or cuts.
Character & Product Consistency
Assign each reference one named role and state what may never change.
1990s Tokyo Chase and Rollover Crash
An anamorphic chase that opens at full speed through 1990s Tokyo traffic and climaxes in a rollover explosion the pursuing rider barely survives.
Preserve the exact identity and wardrobe of the male target @target_character_sheet and the female assassin @assassin_character_sheet. Use @landcruiser_sheet as the identity reference for the black 1990s Toyota Land Cruiser. Use @kawasaki_ninja_sheet as the identity reference for the green Kawasaki Ninja motorcycle. Use @tokyo_street_mood_1990s and @chase_moodboard_1990s to ground the environment and chase tone. Cinematic anamorphic high-stakes movie chase scene. Begin in the middle of the chase with both vehicles already travelling at full speed through dense 1990s Tokyo traffic. The male target drives the black Toyota Land Cruiser. The female assassin follows closely behind on the green Kawasaki Ninja motorcycle. This is the climax of the chase. The Land Cruiser loses control in traffic, crashes violently, rolls, and explodes in a huge fireball. Because the assassin is following so closely behind, she is suddenly thrown into danger as well. She has only a split second to react. She swerves hard to avoid colliding with the crashing Land Cruiser and the flying debris, narrowly misses the wreck, briefly loses stability, then fights the motorcycle back under control and continues forward at speed. Create maximum perceived speed from the first frame. Use low road-level angles, front-quarter vehicle shots, wheel-level inserts, over-the-shoulder motorcycle pursuit views, compressed telephoto traffic shots, and one brief interior insert of the target reacting inside the Land Cruiser. The camera is repeatedly overtaken by the vehicles, falls behind them, then is rushed past as the crash unfolds. Traffic, barriers, road markings, lights, and water spray pass close to the lens, creating intense foreground parallax and rapid scale changes in frame. Build the scene as one escalating chain of high-speed pursuit, violent crash energy, rolling vehicle momentum, sparks, debris, smoke, and explosion. Keep the Land Cruiser heavy and physical. Keep the assassin fast, precise, and under real pressure as she reacts at the last possible moment, swerves through the danger, stabilises the motorcycle, and emerges clear of the wreck. Compose the action with strong cinematic geometry and visual hierarchy. Use opposing diagonals, asymmetrical subject placement, layered traffic, deep road perspective, compressed depth, and foreground wipes. Let the Land Cruiser dominate the frame during the crash, then shift the visual emphasis to the assassin and the motorcycle as she recovers control and becomes the clear focal point. End with a front-facing tracking shot of the assassin riding toward the camera at speed just after regaining control, still carrying the energy of the evasive move, with the huge explosion of the Land Cruiser behind her. Her posture should show intensity and effort, as if she has only just recovered from the near collision. Firelight, rain haze, neon spill, sodium streetlights, and glossy wet-road reflections. Cinematic anamorphic high-stakes movie chase climax. No music.
- Named identity references for both riders and both vehicles keep wardrobe, faces and paintwork stable across every angle change.
- Starting in the middle of the chase removes all setup time, so the perceived speed is already at maximum on the first frame.
- The camera is repeatedly overtaken and left behind, which turns passing traffic and barriers into strong foreground parallax.
3 identity sheetsIdentity & wardrobe preserved1m18s chase
Courier Chase with Five Locked References
A motorcycle chase where five references separately fix the hero, the pursuers and each machine, distinguished by light colour.
Use the provided references consistently across the full 30 seconds: Image 1 is the first faceless black-armored chaser rider; Image 2 is Kestrel's charcoal courier motorcycle with amber light strip; Image 3 is the dark chaser motorcycle with red taillight and no amber; Image 4 is Kestrel, the broad-shouldered slicked-back male hero in a single-shouldered charcoal jacket with an amber sash; Image 5 is the second faceless black-armored chaser variant. Kestrel stays in front and the two dark pursuit riders stay behind or beside him as visual pressure. Create an original high-speed dark-fantasy motorcycle pursuit scene, 30 seconds, very fast-paced, readable, designed as an edit-friendly trailer cut with rapid cinematic shots. No background music, no soundtrack music, no subtitles, no text, no logos. Setting: elevated highway through a dense dystopian megacity, monolithic concrete arcologies, industrial haze, flat overcast daylight, no rain, imposing and orderly rather than chaotic. Empty roadway, brutal concrete barriers, smoke, sparks, glowing energy trails, and stylized road-impact flashes. FAST 12-SHOT STRUCTURE: SHOT 1, 0:00–0:02 — Cold open. A bright energy flare streaks past the camera toward the highway, motion-blurred, then blooms behind Kestrel's bike in a dramatic orange-black shockwave. Camera shakes. Kestrel is already in front, escaping. SHOT 2, 0:02–0:04 — High aerial reveal. Three motorcycles tear along the elevated highway far below, Kestrel's amber light strip visible at the front, two matte-black pursuit bikes behind in staggered formation. Camera dive accelerates downward. SHOT 3, 0:04–0:06 — Extreme low road-level shot. The hero bike blasts over the lens, amber strip streaking; two dark pursuit bikes thunder after him with red taillights and black armor. Heavy motion blur, road grit, heat shimmer. SHOT 4, 0:06–0:08 — Close-up on Kestrel. Slicked-back wet ash-grey hair, sharp masculine face, amber sash whipping violently, gloved hand twisting the throttle. His eyes stay calm while light flashes bloom behind him. SHOT 5, 0:08–0:11 — Rear chase cam. The left pursuit rider closes in tight and releases a bright warning energy streak. Kestrel drops his shoulder and leans the bike underneath it; the streak passes his shoulder and showers sparks from the concrete barrier. SHOT 6, 0:11–0:14 — Side-by-side pressure. The right pursuit rider surges up beside Kestrel and forces him toward the lane edge. Kestrel kicks the side of his bike frame and snaps the bike sideways in a controlled drift, narrowly avoiding contact while staying ahead. The camera whip-pans with the movement. SHOT 7, 0:14–0:17 — Front tracking angle looking backward. A heavier guided light trail launches from behind, weaving between the bikes with a bright trail. Kestrel cuts through a narrow gap between broken road plates. The guided light hits the road ahead and erupts into concrete dust, debris mist, and black smoke. SHOT 8, 0:17–0:20 — Hero stunt beat. Kestrel and the charcoal motorcycle punch through the blast wash. The bike performs one clean slow-motion barrel-roll through smoke and flying road dust, amber strip glowing, then lands hard with sparks and instantly accelerates. Make the rotation clean and physically readable. SHOT 9, 0:20–0:22 — Pursuit rider close-ups. Rapid cuts: faceless black mirrored visor reflecting Kestrel's amber light; armored gauntlet gripping throttle; red taillight streak; tire sliding through sparks. The two pursuit riders regroup behind him, still closing. SHOT 10, 0:22–0:25 — Power reveal. Low side profile at extreme speed. Kestrel rises upright on the moving bike, balanced and confident, turning backward toward the two riders. Four compact golden magical sigils bloom around his shoulders and hands, spinning like hot geometric halos. The road and city blur around him. SHOT 11, 0:25–0:28 — Climax escape. The golden sigils fire concentrated beams backward down the highway. The beams carve glowing lines through the haze and strike the road around the pursuing bikes, creating a wall of golden-orange light, smoke, sparks, and shockwave energy. The two pursuit riders disappear into the smoke and fall far behind, ending the chase. Keep it stylized, non-graphic, cinematic, and readable. SHOT 12, 0:28–0:30 — Final hero exit. Medium rear tracking beside Kestrel. He drops back into the seat, leans low over the charcoal bike, gives a small confident smirk, then rockets away down the elevated highway. Smoke columns recede behind him. End with forward acceleration, no title card. Visual style: original premium dark-fantasy action cinema, high quality Unreal Engine cinematic render, modern high-end fantasy game visual quality, not copying any existing franchise characters, armor, weapons, symbols, or scenes. Anamorphic lens, speed-ramped action, rapid cinematic cuts, whip-pan transitions, camera shake from road impacts, heavy motion blur, atmospheric haze, film grain, cinematic color grade, strong silhouettes, consistent character and vehicle design, dynamic but readable action, no rain. Audio instruction: no background music, no soundtrack music. If audio is generated, use only sparse cinematic sound effects such as engine roars, wind rush, energy pulses, road-impact booms, tire skids, debris impacts, and magical beam crackle.
- Each vehicle is identified by a unique light signature — amber strip versus red taillight — so the model never confuses them.
- Assigning references one at a time to rider and machine keeps identity stable during fast motion.
- Colour coding does the work that faces cannot when riders are helmeted.
5 locked referencesHero, pursuers, machinesNo identity swaps
Office Washroom Fashion Transformation
A fashion transformation reel where the woman and the room stay pinned while only the outfits change.
Create a 30 second photorealistic fashion transformation video in a 16:9 landscape frame. A stylish young woman with long softly waved brown hair, warm medium skin, round black glasses, small earrings, natural makeup, and consistent facial features stands in the same modern office washroom or dressing area for the entire video. The background has large charcoal gray stone tiles, a pale ceiling, a slim black wall rail on the left, and a narrow metal partition line on the right. Keep every architectural line perfectly fixed across all cuts. Camera is locked on a tripod at eye level, medium full shot from mid thigh upward, using a natural 35 mm equivalent smartphone lens. The subject remains centered with enough space on both sides for the landscape composition. No camera shake, zoom, reframing, or perspective change. Use crisp realistic detail, true skin texture, fine hair strands, believable fabric folds, accurate hands, subtle breathing, and tiny posture adjustments. Lighting is soft cool overhead office lighting with gentle facial fill, mild reflections on the gray tiles, consistent exposure, and realistic shadow direction. Begin with her palm very close to the lens, briefly obscuring most of the frame. She pulls her hand away and reveals the first outfit, a sleeveless pale blue floral office dress with a light scarf over one shoulder. She looks calmly into the camera, lowers her arm, places one hand on her hip, glances upward with a mildly unimpressed expression, then folds her arms. Match this exact folded arm pose for the first invisible jump cut. Across the next twenty four seconds, reveal nine distinct office outfits through clean pose matched cuts timed to the music. Use a lemon yellow floral kimono blouse, a relaxed ivory button shirt with navy trousers, a fitted black sleeveless top with dark tailored pants and a brown belt, a soft blush pink top with black trousers, a deep green crew neck blouse, a vivid blue paisley shift dress, a black and white dotted peplum blouse, a camel blazer over a cream top, and a final elegant burgundy wrap dress. Between changes, give her natural confident gestures such as a small shoulder bounce, two thumbs up, hands settling on hips, crossing her arms, turning her chin, smoothing a cuff, lightly flicking her hair, pointing toward her cheek, and smiling directly at camera. Each gesture should begin in one outfit and end in the next so the cut feels practical and intentional, never like body morphing. Hold each look long enough to read clearly, roughly two seconds per outfit, with cuts landing on strong beats. Preserve identical body position, hair direction, glasses placement, limb anatomy, background geometry, and lighting at every transition. Avoid warped fingers, changing facial identity, floating clothing, cloth melting, duplicated accessories, sudden camera motion, or artificial beauty smoothing. For the final four seconds, she lands in the burgundy dress with one hand on her hip, gives a warm playful smile, taps one finger lightly against her cheek, then reaches toward the lens until her palm fills the frame, creating a natural practical ending. Do not add captions, logos, watermarks, interface graphics, or generated text. Music should be an upbeat polished fashion pop instrumental at about 112 beats per minute with tight percussion, light bass, finger snaps, bright synth accents, and clean beat drops for every outfit change. Add subtle realistic clothing movement, bracelet clicks, and a soft hand whoosh at the opening and closing. The finished result should feel like a real creator filmed several office looks in one location and edited them precisely to music.
- The location is described in fixed architectural detail so every cut returns to exactly the same space.
- Facial features and hair are locked once, which is what allows rapid outfit swaps to read as one person.
- Landscape framing is stated up front, keeping the composition consistent across changes.
Woman & room pinnedOnly outfits changeTransformation reel
Fifty-Reference Previz Character Replacement
Fifty reference images drive a cel-animated remake of a previz, with an absolute rule that only one human may ever appear.
キャンバス上にある情報を全て使い、以下の内容の動画を作って。 （以下） Seedance 2.5用プロンプト｜占獣・一人芝居版 生成目的 参照画像50枚を用い、約15.18秒、16:9の高品質な日本製2Dセルカラーアニメーションを生成する。元プレビズの編集点、カメラ軸、画角、被写体サイズ、手の軌道、札の位置、廊下の消失点、動作の緩急を維持しながら、登場人物をオリジナル作品『占獣 / SENJYU』の主人公・我妻學へ置換する。 この映像に存在する人間は我妻學ただ一人である。敵役、対戦相手、廊下奥の人物、分身、残像、影人間、鏡像、反射内の人物、背後の人物、観客、通行人を一切生成しない。前半の正面顔、手元、背面、後半の廊下内の背面人物は、すべて同一時刻の同一人物・我妻學である。カメラが切り替わっただけであり、二人が向かい合っている場面ではない。無人廊下の奥には何者も存在しない。 参照画像の読み方 Image 1〜24はセルカラーの時間順キー画像。Image 25〜48はImage 1〜24と同一番号で対になる深度マップ。Image 49は我妻學のキャラクター固定資料。Image 50は占術札の固定資料。 各カラー画像と深度画像は必ず一対として扱う。カラー画像から顔、衣装、線、色、札の意匠、背景素材を取得し、同番号の深度画像から前後関係、被写体距離、手と顔の重なり、札同士の奥行き、廊下の消失点を取得する。深度画像の白は近景、黒は遠景。深度画像の無彩色を完成映像の色として採用しない。 キャラクター固定 我妻學は小学生男子。短く乱れた黒髪、鮮やかな青い瞳、少年らしい小柄で細身の体格。濃紺の半袖夏制服、白いパイピング、濃紺の短パン。すべてのカットで顔、年齢、髪型、目の色、体格、袖丈、襟、服の配色を固定する。成人化、長身化、筋肉質化、別人化、女性化を禁止。手前に大きく写る手も必ず學本人の手であり、第三者の手ではない。手指は片手につき5本。手首、肘、肩の接続を自然に保ち、指の増殖、癒着、欠損、左右反転を避ける。 占術札固定 トランプではなく『占獣』独自の占術札。黒藍色の薄い長方形、細いシアン発光縁、九星・羅針盤・星図を抽象化した幾何学意匠。ハート、スペード、ダイヤ、クラブ、ジョーカー、数字、英字、読める文字、既存カードゲームの記号を表示しない。札は硬質な紙または薄い術式媒体として扱い、ゴムのように曲げない。浮遊時は各札が独立した平面を保ち、互いに貫通しない。発光は輪郭と術式線に限定し、画面全体をネオンで白飛びさせない。 映像スタイル 完成された劇場品質の2Dセルアニメ。鮮明で整理された線画、2〜3段階のセル影、抑制された濃紺・青緑・シアンの色設計。写真、実写、3DCGレンダー、ゲーム画面、モーションコミック、ラフ絵、鉛筆線へ変化させない。背景は暗い施設廊下だが黒潰れさせず、壁、床、扉、天井灯、奥行きを読める状態にする。被写界深度は強くしすぎず、参照キーにある手、顔、札の輪郭を維持する。 ショット構成 Shot 01｜0.000〜0.346秒｜極端な顔寄り Image 1からImage 2へ。學の片目、顔の一部、上げた手を極端な近距離で捉える。カメラ位置を動かさず、呼吸と視線の微細な緊張だけを補間する。手前の手は學本人の手。別人物のPOVや、誰かが顔を覆っている構図に解釈しない。Image 2の直後にハードカット。 Shot 02｜0.346〜1.093秒｜占術札の手元 Image 3からImage 4へ。札群と學の手だけを俯瞰寄りで映す。人物の顔や別の身体を追加しない。手の圧と術式反応によって札の重なりがわずかに変化する。札は同じデザイン、同じ枚数感、同じ平面性を維持。次ショットへハードカット。 Shot 03｜1.093〜4.042秒｜正面で札を制御 Image 5→6→7→8。正面寄りの學が、顔の横に掲げた札を指先で制御し、手首を下げ、指を組み替え、解放直前の形へ移行する。カメラは基本固定。學の頭部位置と肩線を安定させ、手だけが弧を描いて動く。Image 5〜8のポーズ間を滑らかに補間するが、過剰な中割りで手をぐにゃぐにゃ変形させない。表情は冷静で集中。口パクなし。 Shot 04｜4.042〜4.768秒｜札群の空間展開 Image 9からImage 10へ。人物は画面に存在せず、占術札だけが暗い空間に複数の距離層で浮遊する。札の移動は小さく鋭い。各札の前後関係は対応深度に従う。新しい札を無制限に増やさない。画面中央に敵や召喚獣を出さない。 Shot 05｜4.768〜6.621秒｜背面から右手操作 Image 11→12→13。學を背後から捉える。右肩、前腕、手首、指先が連動し、空中の札を整列させる。背後に見えるのは無人空間と札だけ。正面にもう一人の學を置かない。背中、首、右肩の接続を固定し、腕の長さを変えない。カメラは固定し、微細なプッシュインのみ許可。 Shot 06｜6.621〜7.605秒｜正面の腕・拳 Image 14→15→16。ハードカットで正面へ戻り、學が腕を伸ばした状態から指を巻き込み、拳を上げる。右手の軌道、顔の中心位置、肩幅を参照どおりに維持。拳は顔を完全に隠さない。決意は目線と手の収束で表現し、叫びや口パクを追加しない。 Shot 07｜7.605〜8.642秒｜デジタル表示 Image 17からImage 18へ。壁面表示だけのインサート。人間、手、影、反射を追加しない。表示面は同一位置で、発光の変化だけを見せる。画面上に字幕、UI、説明文、ロゴを追加しない。表示を読ませることより、緊張の時間圧を伝える。 Shot 08｜8.642〜10.028秒｜無人廊下への前進 Image 19からImage 20へ。完全に無人の長い廊下。中央消失点へ向かう直線的で高速なドリーイン。扉、天井灯、床線の間隔が物理的に縮まり、正しい遠近法で加速を示す。廊下奥に人物、標的、怪物、影を生成しない。左右へ蛇行、ロール、手持ち揺れを加えない。 Shot 09｜10.028〜15.148秒｜背面投擲 Image 21→22→23→24。無人廊下の手前に學一人だけが背中を向けて立つ。開始時に右肩と前腕で投擲準備。次に複数の占術札を片手の周囲へ浮上させ、両腕のバランスを取りながら投擲方向を定める。札が腕の振りと同期して無人廊下の消失点へ高速移動し、最後は學が腕を伸ばしたフォロースルーで終える。札は画面奥へ小さくなり、正しい遠近縮小とモーションブラーを持つ。札が向かう先に人物や標的を出さない。學の身体は一体のみで、残像による複数腕や複数身体を作らない。 編集・時間・カメラ 総尺は元動画と同等の約15.18秒。9つの編集ショットはすべてハードカットで接続し、異なるアングル間をモーフィングしない。各ショット内部のみSTART→ACTION KEY→ENDを補間する。カメラ移動を許可するのは、Shot 08の直線ドリーインと、参照から読み取れるごく小さな寄りのみ。勝手な旋回、360度回転、オービット、魚眼化、ズームアウト、別アングル追加を禁止。廊下の左右反転を禁止。 動作と物理 人物の重心、肩から肘、肘から手首、手首から指の連鎖を保つ。札が手を貫通しない。札同士が融合しない。札は投擲方向へ速度を得た後、慣性に従って廊下奥へ進む。発光軌跡は短く、札の数を誤認させる長い残像を作らない。髪、襟、袖には動作に応じた最小限の追従を付ける。床接地が見える場合は足を滑らせない。 絶対除外 二人目の人物、敵、対戦相手、廊下奥の人影、同じ學の複製、黒い分身、幽霊、残像人物、鏡像、反射人物、群衆、手だけの第三者、別キャラクター、成人、女性、顔の変化、衣装変更、長袖化、別制服、トランプ、ハート、スペード、ダイヤ、クラブ、既存カードゲーム、銃、ナイフ、剣、流血、接触戦、人物への攻撃、召喚獣、字幕、台詞テロップ、ロゴ、透かし、読める文章、画面分割、絵コンテ枠、参照番号表示、低解像度、実写、3DCG、粘土質、過度なグロー、色飛び、黒潰れ、指の増殖、腕の増殖、身体の複製、顔の溶解、札の融合、背景のワープ、廊下の左右反転。 最終到達像 完成映像は、我妻學一人が占術札を静かに支配し、無人の長い廊下へ一斉投擲する、一人芝居の高速アクションである。人物同士の戦闘にはしない。元プレビズのショット順、カメラ軸、動作ピーク、時間圧を保ちつつ、すべてを『占獣』固有のセルカラー世界へ変換する。
- The previz's edit points, camera axes and subject sizes are preserved while only the character is swapped.
- An exhaustive ban list — no opponents, doubles, reflections, bystanders — closes every way a second figure could appear.
- Explaining that front and back views are the same person at the same moment resolves the model's usual misreading.
50 reference imagesPreviz-driven remakeOnly one human allowed
Chinese Classical Dance Portrait Short
A 30-second classical Chinese portrait piece driven by depth video, a nine-grid reference sheet and reference BGM, with three performers kept strictly separate.
3/ Seedance 2.5 Prompt 【任务】 生成完整 30 秒中国古风人物小传短片。 严格按照时间轴、多模态素材映射、人物隔离和参考音频执行，不自由修改镜头与剧情。 【参考绑定】 - Depth 视频：只控制约 0–5s、10–18s、25–30s 三段核心舞蹈 - 多视角头像 + 全身图：只锁定主舞女 - 九宫格：按编号调用妆造、乐器与剪影镜头，禁止串格 - 场景图：全片保持同一个古风雅室 - 参考 BGM：作为唯一音乐，从 0s 播放至 30s 【人物隔离】 主舞女、古筝女和琵琶女必须是三位不同角色。 Grid 1–3：只出现主舞女 Grid 4–5：只出现古筝女 Grid 6–7：只出现琵琶女 Grid 8–9：以主舞女剪影为主 配角造型更素、光线更收，不抢主角。 【参考时间轴】 0–5s：主舞女舞蹈起势 5–6.5s：描眉 6.5–8s：抿唇 8–10s：插发簪 10–18s：主舞女舞蹈中段 18–19.5s：古筝女全景 19.5–20.5s：古筝手部特写 20.5–21.5s：琵琶女全景 21.5–22s：琵琶手部特写 22–23.5s：纱帘剪影全景 23.5–25s：纱帘剪影特写 25–30s：主舞女舞蹈收势 【画面要求】 真实古风雅室，以烛火和宫灯作为主要光源。 皮肤保留自然纹理，不要磨皮、塑料感和均匀棚拍光。 飘带、发簪、纱帘与琴弦保持真实材质和运动惯性。 所有动作重拍与镜头切换尽量跟随参考 BGM。 【总要求】 总时长 30 秒。 人物、动作、场景、镜头和音乐沿着同一条时间轴推进。 结尾回到主舞女，不使用配角或空镜收尾。 禁止串脸、镜头错序、音乐错位、自由改剧情、字幕、Logo 和水印。
- Each reference asset is bound to a specific job and a specific time range, so nothing bleeds between them.
- An explicit character isolation block prevents the three performers from merging into one face.
- The timeline assigns every second, which is what makes multimodal control hold for a full 30 seconds.
Cyber-Wuxia Series Trailer
An epic series trailer assembled from eighteen reference images, blending wuxia, desert wasteland and cyber-north factions into one world.
基础设定：一段25S史诗赛博武侠风格的美剧的预告片。 角色/场景/道具设定： 黑衣女子，夜刃：image1，武器为短刀。 听渊：image2，武器为长剑。 西部猫：image3 闪电丧尸机器人：image4 青衣射箭女：image5 红衣女，南宫无双：image6，image18 ，南宫无双的手下 image7。 巨型沙虫：image8，高度有几十米，上百米。 粉短发女：image9，image 17 秦昭宁：image10，全身形象image11，武器image12。 楚霸王：image13。 北境的丧尸机器人：image14 酒吧内部：Image 15 沙漠场景：image 16 视觉基调： 好莱坞史诗奇幻美剧与末世废土大片融合质感，整体参考美剧史诗大片的沉重史诗感与美国大片预告片的强视觉冲击。画面具有粗粝胶片颗粒感、。世界观呈现中式武侠、古代战争、赛博北境、沙漠废土，巨型怪物并存的混合异世界。整体质感荒凉、危险、宏大、硬核，带有强烈的末世生存感和宿命感。 光影色调： 用高反差电影光影，强逆光、侧逆光和局部冷光结合。沙漠酒馆线以昏黄油灯、破窗夕阳、琥珀色沙尘光为主，暗部压深，人物轮廓被暖光勾出。北境雪山线以冷白、铁青、蓝灰色为主，暴雪漫反射形成冰冷压迫感。整体调色保持青橙对撞，高光偏琥珀与焦土黄，阴影偏铁青与褪色蓝灰。 摄影机参数与运镜基调： 采用电影级全画幅数字摄影机质感，ARRI Alexa 65 / RED V-Raptor 级别画面，16:9 横版画幅，24fps 主体电影帧率，部分动作镜头使用 60fps / 120fps 升格慢动作。镜头语言以 24mm、35mm、50mm 电影定焦为主，人物压迫感使用 35mm 近景手持跟拍，史诗大场面使用 24mm 广角低角度仰拍与航拍大全景，人物情绪特写使用 50mm 浅景深镜头。景深控制明显，背景虚化自然，焦点在人物眼神、武器、箭矢、飞针、机械电弧之间快速切换。 其他设定：动作凌厉。画面强烈的视觉冲击。画面带有强烈的冲击力和打击感。整个画面有节奏感和电影感，仅生成环境的音效，不要配背景音乐。真人写实史诗电影风格。画面禁止出现任何字幕和任何白色的字体；画面出现文字，采用透明字体。完全真人实拍质感。 画面内容： 0-4秒：画面建立在一间沙漠废土酒馆内部。中景环绕运镜，听渊、夜刃、西部猫被一圈敌人围住，敌人中混杂着赛博改造打手和闪电丧尸机器人带来的机械手下。听渊穿青衣，单手持长剑，剑尖微微下垂，眼神冷静但紧绷；夜刃黑衣站在阴影中，手持短刃半出鞘，脸上没有表情；西部猫站在桌面上，牛仔帽压低，爪子慢慢摸向腰间武器。。 4-8秒：硬切北境雪地。画面骤然变冷，风雪呼啸。秦昭宁从厚厚积雪中猛然睁眼苏醒，面部特写，睫毛和发丝结着冰霜，脸上带着伤口和血迹。远处暴雪深处，隐约出现数双红色眼睛，忽明忽暗，像有什么东西在雪雾中盯着她。音效只保留风暴声和低沉丧尸嘶吼。突然，几个塞外丧尸从雪地里破雪而出，身上挂着残破甲片，动作僵硬却极快，挥舞弯刀冲向秦昭宁。镜头采用手持近距离跟拍，雪粒猛烈撞击镜头，压迫感极强。 8-11秒：硬切回沙漠酒馆内部。，一支箭从二层廊台方向破空射下，带着尖锐风声击中闪电丧尸机器人的胸口装甲，电光爆裂，火星四溅。整个酒馆短暂陷入半秒静止。听渊、夜刃、西部猫和敌人同时抬头看向楼上。镜头快速上摇，二层青衣射箭女出现，长弓拉满，。她不说话，只是冷静地瞄准第二个目标。镜头强调箭矢、弓弦、她的眼神和楼下众人的震惊反应。 11-16秒：硬切北境场景，紧接秦昭宁被围攻。秦昭宁从雪地中翻身而起，抓起红缨长枪，低角度镜头捕捉枪尖划破积雪的瞬间。几个塞外丧尸扑到她面前，她挥动长枪横扫，枪杆带着沉重破风声击碎丧尸兵器，枪尖刺穿冰雪与残甲。动作干净、狠、带有古代女将军的力量感。危机仍未解除，更多塞外丧尸和半机械化丧尸机器人从风雪中冲来。就在秦昭宁被逼退半步时，远处传来战马嘶鸣。风雪深处，楚霸王骑着黑马冲出，巨型武器拖出一道雪雾。他从秦昭宁身侧掠过，低角度跟拍马蹄踏碎冰层，随后巨刃横扫，多个丧尸机器人被直接劈飞，机械零件、冰屑和黑血同时炸开。秦昭宁回头看向他，脸上第一次出现震惊表情，像是无法判断这个突然出现的人究竟是救兵还是更大的怪物。 16-20秒：硬切沙漠天空，南宫无双站在飞船甲板前端，红衣金纹在狂风中翻动，姿态极稳，像整个沙漠都在她脚下。她缓缓抬手，周围无数金属碎片、飞针、断裂兵器和机械零件悬浮起来，形成一个危险的金属环。镜头环绕她半圈，突出她冷静、华丽、强势的压迫感。远处沙海开始下陷，巨型沙虫从地下缓缓升起，没有完全露出全貌，只显现出巨大背脊、鳞片和吞噬沙丘的阴影。沙虫低下头，像在向南宫无双臣服。飞船下方，她的巨人手下站在沙漠中，仰望她和沙虫，脸上是近乎膜拜表情。画面安静但极度危险。 20-25秒：硬切高速沙漠车内视角。粉色短发女子驾驶一辆越野车的车内画面，粉色短发女子单手握方向盘，另一只手猛地拉动档杆，车身贴着沙丘猛烈抖动，几乎要翻车。听渊表情紧张，夜刃依旧冷静，但手已经按住车门边缘。粉色短发女子回头看她们一眼，带着不合时宜的轻松和疯劲，用中文大声说：“坐稳了，侠女，这车没有刹车！” 越野车猛然加速，非常猛的惯性，后座的听渊和夜刃往后座猛的后躺。切换车外航拍视角，越野车快速行驶在沙漠中。
- Every reference is numbered and assigned to a named character, weapon or location before any shot is described.
- A single visual tone statement covers grain, contrast and mood, so eighteen sources still cut together.
- Trailer format gives the model permission to jump between factions without needing narrative connective tissue.
Gothic Twins Previz-Driven POV
A POV piece where a five-image reference stack — including a 30-second previz — controls staging, framing and the 9:16 safe area.
参照素材: Image1: 銀髪ゴスロリ双子の顔立ち、目つき、髪型、衣装、黒い光輪、全体配色の最優先参照。元画像の構図は使用しない。 Image2: キャラクター設定画。正面・背面の髪型、体型、黒いゴスロリ衣装、靴、表情設計の参照。 Image3: 実写ゴシック寝室の舞台参照。部屋の構造、天蓋ベッド、レース、ベルベット、暗色木材、窓、ランプ、家具、床、現実の材質感と奥行きを参照する。壁面の十字架や宗教記号は使用しない。 Image4: 30秒プレビズ。CUT 01〜06の人物配置、画角、中央9:16セーフ、カメラ移動、カメラ高、アングル、終端構図を参照する。画像内の人物は演出確認用マネキンであり、完成映像ではImage1とImage2のキャラクターへ置き換える。 Image5: 立ち姿の灰色の兎のぬいぐるみ。現実的な体型、毛足、垂れ耳、暗い赤色のガラス製の瞳を参照する。 固定条件: 30秒、16:9横型、視聴者がその場にいるPOV視点。9:16へ中央トリムしても双子の顔、手、兎のぬいぐるみ、主要な演技が残るよう、関心事を常に中央へ集める。 実写とセル画アニメの明確なハイブリッド映像。部屋、家具、寝具、ランプ、窓、床、兎のぬいぐるみは実写フォトリアル。双子だけを高密度なセル画アニメとして描く。キャラクターの接地影、落ち影、環境光、ランプ光、遮蔽、色かぶりは実写背景と物理的に一致させる。 背景は全編で深い被写界深度。絞りF5.6〜F8相当の見え方とし、前景・中景・後景のレース、ベルベット、木目、金属、ガラス、カーテン、寝具、床、壁の質感と部屋の立体構造を明瞭に保つ。背景を雰囲気だけのボケにせず、実写空間として読める情報量を維持する。自然なレンズ描写、現実的なハイライトの減衰、微細なセンサーノイズ、実写らしい影と反射。 双子は瓜二つの美少女アニメキャラクター。Image1とImage2を最優先し、顔立ち、目つき、銀髪ツインテール、額と耳が見える髪型、黒いリボン、黒いゴスロリ衣装、黒い光輪を全カットで維持する。キャラクター配色は均一なベタ塗り、段階的な色調、強いセルシェーディング。主線は太さが安定した、ムラのない鮮明な黒線。2024年制作の日本ヴィンテージセルアニメ映画を思わせる精密な作画、高い描き込み、滑らかな動き。 双子の瞳は全編で澄んだグレー。白目は清潔な白。白いまつ毛、白いアイライン、白い上下まぶたの線、白い目の輪郭線、長い下まつ毛を維持する。目を赤くしない。瞳、白目、目の縁に充血や血管を一切出さない。 赤色は兎の暗赤色のガラス眼と、最後に双子の頬へ現れる上品な朱色の紅潮だけに限定する。頬の紅潮は目や鼻へ広げず、白い肌との色彩コントラストを明瞭にする。 カメラはPOVらしい距離感。全編にごく軽い手持ちの揺れと呼吸に同期する微細な上下動を入れるが、顔と背景の可読性を損なわない。各カットでは記載した主要カメラワークを優先し、不要な複合移動を加えない。 音楽なし。環境音もできるだけ入れない。日本語の女性ボイス、近距離で静か、囁きに近い自然な発声。台詞は指定どおりに発話し、字幕や画面文字は出さない。 全体設計: 前半15秒は静かな執着と親密さを積み上げる。後半は「裏切ったら……」の余韻から静かな笑いへ移り、3秒だけ照明とPOVの後退によるホラーへ反転し、最後の9秒で緊張を甘く裏返す。結末の主役は、澄んだグレーの瞳、青白い肌、朱色に染まる頬、蠱惑的かつ恍惚とした微笑。ホラーを引きずらず、怖さより可愛さと危うい魅力を最終印象にする。 [00:00-00:05] 動作・演出: 実写のゴシック寝室。妹が天蓋ベッドに腰掛け、ベッド上で立ち姿を保つ灰色の兎のぬいぐるみの頭を、指先でゆっくり撫でる。ランプの実写炎がわずかに揺らめき、妹の白い髪と黒い衣装へ硬いセル影を落とす。妹は撫でる手を止めず、最後に視線だけをカメラへ向ける。 カメラ: MCU、アイレベル0度。妹の上半身から顔のCUへ、0.8mのスロードリーイン。中央9:16セーフ内に顔、手、兎を維持する。 音声: 衣擦れ、毛足を撫でる小さな音、ランプの微かな燃焼音、遠い室内音。妹「コウテイペンギンっていいよね。」 [00:05-00:10] 動作・演出: 姉が妹の背後から静かに入り、妹の首から上胸部へ執着するように両腕を回して抱きつく。締め付ける暴力ではなく、逃がさない親密さ。二人の黒い光輪が不規則に弱く明滅する。二人は澄んだグレーの瞳でカメラをまっすぐ見つめる。 カメラ: MS、ハイアングル35度。頭上から0.6mのゆっくりしたクレーンダウン。終端で二人の顔を中央9:16セーフへ重ねる。 音声: ベッドの沈む音、布の擦れる音、低い室内残響。姉「アデリーもいいわよ。」 [00:10-00:15] 動作・演出: 二人の頬と髪が触れるほど顔を寄せる。表情は無機質な静けさから、口元だけがわずかに歪む危うい微笑へ移る。瞳はグレーのまま澄んでおり、背景には実写の天蓋、ランプ、レース、木製家具が鮮明に残る。 カメラ: CU、ローアングル15度。左の顔から右の顔へ20度だけゆっくりパンし、二人の間へ戻ってセンターで止める。 音声: 部屋の環境音を少し絞り、浅い呼吸を近くで聞かせる。妹「イワトビも……すき」 [00:15-00:18] 動作・演出: 二人は密着したまま、視線をカメラから外さない。妹の口元だけが小さくほどけ、姉はその笑いを共有するように僅かに頬を寄せる。目には異常を起こさず、静止に近い演技で不穏な間を作る。 カメラ: タイトCU、アイレベル0度。前カットのセンター位置から継続し、0.15mだけ極めて遅いマイクロプッシュイン。 音声: 0.4秒の静かな間のあと、妹の小さな含み笑い「フフッ」。BGMなし。 [00:18-00:21] 動作・演出: 一瞬だけホラーへ反転する。枕元のランプが乾いた音と同時に消え、冷たい窓光だけが実写の部屋の輪郭、レース、木材、二人のシルエットを薄く残す。二つの黒い光輪が闇の上で短く明滅し、兎の暗赤色のガラス眼が反射光を一点だけ返す。双子は動かず、目を赤くしない。最後の0.3秒でランプが再点灯し始める。 カメラ: MCU、ダッチアングル4度。POVが反射的に0.25mだけ鋭く後退するワンアクション。後退後は揺れを止め、暗闇を1拍だけ保持する。 音声: ランプが消える乾いたクリック、短い低周波の衝撃音、直後に無音へ近づく。叫び声、金切り声、ホラー音楽は入れない。 [00:21-00:30] 動作・演出: 暖かなランプ光が滑らかに戻り、恐怖の硬さが解ける。二人はカメラへ少しだけ身を寄せる。妹が「なんて……ね」と甘く囁き、姉も同時に目を細める。二人の白い肌は青白く清潔なまま、頬だけが時間をかけて上品な朱色へ染まる。二人はカメラを受け入れるような蠱惑的かつ恍惚とした微笑を浮かべる。澄んだグレーの瞳には柔らかなランプのキャッチライト。赤い光や充血ではなく、白い肌と朱色の頬の対比で陶酔感を表現する。実写背景のレース、天蓋、木目、ランプ、兎の毛足は最後まで鮮明に見える。 カメラ: CU、アイレベル0度。前カットのダッチを水平へ戻してから、二人の顔へ0.35mの非常に遅いドリーイン。終端は二人の顔を左右対称に中央へ置き、頬と目、背景の実写質感が同時に読める距離で停止する。 音声: ランプが戻る小さな点灯音、寝具の僅かな沈み、近い呼吸。妹「なんて……ね」。語尾は蠱惑的で甘く、笑みを含ませる。声色と表情で表現する。 終了フレーム: アイレベルの左右対称CU。二人が頬を寄せ、澄んだグレーの瞳でカメラを見つめ、白い肌と上品な朱色の頬を対比させた、蠱惑的かつ恍惚とした微笑。黒い光輪は安定して弱く輝く。実写のランプ、天蓋、レース、木目、兎の毛足を深い被写界深度で鮮明に残し、0.5秒静止保持する。 避けること: 目の充血、赤い白目、赤い虹彩、赤い瞳孔、目の血管、赤い目の縁、泣き腫らした目、目周辺への赤い照明。最終カット以外の頬の強い紅潮。頬の赤みが目や鼻へ広がる表現。 浅すぎる被写界深度、背景ボケ、クリーミーなボケ、顔以外の全面ぼかし、実写背景の情報消失、イラスト背景、アニメ背景、絵画化した家具、人工的な被写界深度処理。 キャラクターの実写化、背景や兎のアニメ化、セル画キャラクターと実写空間の影・光・接地の不一致。 Image1の構図の複製。壁の十字架、磔刑像、宗教記号。流血、傷、暴力、首を締める表現、過度にグロテスクな演出、長すぎる暗転。 双子の顔、髪型、衣装、体型、光輪の変形や入れ替わり。第三の人物、余分な腕や指、融合した身体、兎の増殖や変形。 字幕、台詞文字、ハート記号、ロゴ、透かし、UI、カメラ注釈を完成映像へ表示すること。 激しい手ブレ、過剰なローリング、急すぎるズーム、顔や手の見切れ、中央9:16セーフから主要演技が外れること。
- One reference is a previz whose mannequins are explicitly flagged as placeholders, so the model replaces rather than copies them.
- Composing for a centre-safe 9:16 crop inside a 16:9 frame makes one render usable on two platforms.
- Each image is scoped to exactly what it controls — face, costume, room, staging, prop — with no overlap.
Rapper Identity Replacement Performance
A performance clip where one reference image is declared to completely replace all previous performer references, down to beard and shirt stripes.
@Image1 is the absolute reference for THE RAPPER and completely replaces every previous performer reference. Preserve his exact identity: middle-aged man with a high receding hairline, short salt-and-pepper hair, thick dark eyebrows, dark eyes and a full beard with strongly defined white-gray sections. Preserve his stocky build, black-white-dark-green horizontally striped T-shirt with black chest pocket, sand-colored knee-length chino shorts and chunky off-white sneakers. No changes to his face, body, hair, beard, clothes or proportions. A 30-second single continuous live stadium rap performance captured horizontally on an iPhone from the front audience section. Authentic handheld fan footage: physical hand tremor, operator breathing, imperfect reframing, rolling shutter, digital-zoom softness, momentary autofocus hunting and compressed phone-microphone sound. No cuts. The first frame already shows THE RAPPER full-body on the right third at the end of a stage runway. A huge sold-out stadium surrounds him. Exactly four adult backup dancers wait several meters behind him. Emerald, white and black LED graphics echo the stripes of his shirt. The stage floor remains solid, flat and continuous. A heavy original grime beat begins: deep sub-bass, dry kick, snapping snare and minimal low synth. The iPhone rapidly pinches from 1× to a shaky 5× digital zoom, briefly overshoots, then locks onto THE RAPPER in a full-body composition. Focus stays wide enough to preserve his feet and choreography. He begins rapping with a low-mid, forceful cadence and exact lip synchronization: THE RAPPER: “Walk in steady, put the weight on the beat, Every bar lands, every move stays clean. Hands up high when the bass comes down, I don’t chase the wave—I shake the whole ground!” Only these words are spoken. Each line is delivered in one controlled breath. On the first bar he performs two violent shoulder hits, a chest pop and a sharp forearm lock. His shirt and beard react naturally to momentum. On the second bar he executes fast heel-toe pivots, crosses one foot behind the other and glides sideways while keeping his heavy body convincingly grounded. The camera operator struggles to keep his sneakers in frame, corrects downward and catches the complete footwork. On the third bar the four dancers join in perfect synchronization. THE RAPPER leads a hard sequence: right stomp, left stomp, elbows strike outward, torso snaps backward, hands shoot overhead. Every movement lands precisely on a kick or snare. The instrumental cuts for one beat. He holds a deep wide stance, eyes fixed on the upper tiers. His chest rises with one visible breath. He shouts the final line while performing a rapid three-step, a controlled 180° pivot and one enormous downward arm strike. On “GROUND,” he stomps once. The bass returns with a massive impact; the LED floor sends a broad solid emerald light wave across the stage. The entire stadium copies his movement. The phone shakes from thousands of spectators stomping together. He breaks into a confident grin but continues bouncing in time, pointing from one side of the stadium to the other. The operator zooms rapidly back through 3× and 1× to 0.5× ultra-wide while turning 160° away from the stage in one continuous handheld sweep. Exposure briefly pumps, then recovers. Finish on the full stadium bowl: tens of thousands of people across every tier performing the same shoulder-hit and stomp combination, emerald wrist lights moving in broad geometric waves, stage remaining on the far-left edge. Audio continues with the crowd chanting “SHAKE THE GROUND,” live bass vibration and realistic phone compression. Rich emerald and white light, warm skin and deep blacks. Clear air without haze, smoke, confetti, mist, sparks or airborne particles.
- Declaring the reference absolute and superseding is an effective way to clear conflicting earlier context.
- Identity is described in enumerable traits — hairline, beard sections, build, striped shirt — which survives motion.
- Wardrobe is locked alongside the face, so the performer stays the same person across energetic movement.
Tactical Action Demo One-Take
A continuous tactical fight demo that keeps the reference face but deliberately changes the wardrobe to a new tactical loadout.
SEEDANCE 2.5 — ACTION DEMO (15 Seconds | One Continuous Take) Character Lock Alex: Keep the exact same facial features, hairstyle, eye shape, and expression from the reference image. Different wardrobe: matte black tactical bomber jacket, charcoal compression shirt, dark tactical cargo pants, fingerless gloves, lightweight combat boots. Enemy: Athletic opponent in a dark gray tactical hoodie, black cargo pants, face partially covered. Audio No Music Foley Only: footsteps, breathing, clothing movement, concrete scrapes, metal rattles, wind. 00:00–00:03 | CHASE OPENING Camera: Chase Shot. Movement: Follow a moving subject quickly along the action route. Speed: Fast, reactive, physically close. Framing: Keep Alex visible while allowing energetic reframing. End: Stay connected to Alex in motion. Action Alex bursts through an industrial alley while the enemy rapidly pursues. She darts between stacked cargo crates, vaults over a low barrier, and accelerates without slowing. The enemy mirrors every movement, staying only a few steps behind. Dust trails behind both runners. Highlight Camera Dynamic handheld stabilization Fast forward tracking Motion blur only on the background Focus remains locked on Alex's face Foley Running footsteps • breathing • jacket movement • gravel • metal rattling 00:03–00:06 | CLOSE-QUARTERS FOOTWORK Camera: Orbit Tracking Shot Movement: Fast 180° orbit while continuously pushing toward both characters. Action Alex pivots sharply into a defensive stance. The enemy advances. They exchange rapid guarded movements using blocks, sidesteps, redirects, and evasive footwork. Alex slips around the opponent with a smooth spin before creating space again. No visible injuries occur. Highlight Camera Orbit around both performers Close facial tracking Quick push-in during every defensive exchange Foley Shoes sliding • fabric movement • glove contact • breathing 00:06–00:09 | ENVIRONMENTAL MOVEMENT Camera: Low Gimbal Tracking Movement: Low-angle tracking beside Alex before rising smoothly. Action Alex slides beneath a metal beam, rebounds to her feet, then vaults onto a concrete platform. The enemy follows closely. Alex uses quick directional changes, forcing the opponent to overcommit before calmly repositioning. Highlight Camera Low-angle cinematic tracking Fast vertical rise Close-up on determined eyes Foley Concrete scrape • landing • jacket movement • footsteps 00:09–00:12 | FINAL EXCHANGE Camera: Handheld Hero Tracking Movement: Tight shoulder-level tracking with subtle camera shake for intensity. Action The enemy rushes forward again. Alex calmly redirects the momentum using controlled defensive techniques before the opponent loses balance and slides safely to a stop several feet away. Alex remains composed, breathing steadily while never taking her eyes off the opponent. Highlight Camera Tight close-ups Fast reframing Cinematic push toward Alex Foley Foot pivots • clothing movement • concrete slide • breathing • wind 00:12–00:15 | HERO ENDING Camera: Slow Hero Push-In Movement: Smooth cinematic dolly toward Alex while slightly orbiting. Action The enemy quietly walks away into the background. Alex stands alone beneath the evening light, adjusts her tactical jacket, looks directly into the camera, and gives a confident, calm expression. Dialogue (Clear Pronunciation) Alex (looking directly into camera): "This is Seedance Two Point Five... using CapCut Video Studio." Alex gives a slight confident nod as the screen naturally fades to black. Highlight Camera Slow cinematic push-in Eye-level framing Sharp focus on facial expression Soft depth of field Foley Light wind • jacket movement • distant ambience • calm breathing Cinematic Settings Photorealism Priority: 100% Human Realism: 100% ARRI Alexa 35 Cooke Anamorphic Lens 4K UHD 24 FPS HDR Lighting Natural Motion Blur Fine Kodak Film Grain Continuous Single Take No Cuts No Music Foley Only
- Separating identity from wardrobe lets the reference control the face while the outfit is freely redesigned.
- The opponent is described only in silhouette and clothing, so no second identity needs locking.
- One continuous take with a defined loadout keeps a fight demo readable at vertical 4K.
Pink Outfit Hip-Hop Identity Lock
A hip-hop studio performance that locks one referenced performer — face, ponytail, full outfit and jewelry — through choreography, a drum solo and set changes.
Use the uploaded reference image as the exact character reference. Preserve her facial identity, eye color, skin tone, hairstyle, makeup, body proportions, and overall appearance throughout the video. She has long black hair in a sleek high ponytail with soft face-framing strands and wears a vibrant hot-pink cropped bomber jacket over a fitted black crop top, a black pleated mini skirt layered over biker shorts, white crew socks, chunky sneakers, silver hoop earrings, layered chain necklaces, and rings. Maintain perfect character consistency in every scene. Create an ultra-realistic premium American hip-hop music video inside a modern industrial studio with glossy black floors, neon pink and blue lighting, graffiti walls, chrome speakers, LED light bars, a professional drum kit, vintage leather furniture, subtle haze, and cinematic contrast. The video opens with an extreme close-up as she confidently adjusts the collar of her pink jacket, stares directly into the camera, smirks, and snaps her fingers to the beat. She turns sharply and walks toward the camera with effortless swagger while her jacket flows naturally. She performs energetic hip-hop choreography with shoulder pops, smooth footwork, body rolls, confident poses, and expressive hand gestures as the camera circles around her with dynamic handheld movement. She jumps onto the drum platform, twirls a drumstick between her fingers, then performs an energetic drum solo with realistic stick movement, powerful cymbal crashes, snare hits, and fast tom fills. The camera alternates between overhead, side-profile, macro close-ups, and dramatic low-angle shots synchronized with the rhythm. The performance continues beside a graffiti-covered roller shutter where she confidently squats, leans against stacked speakers, points toward the lens, and continues lip-syncing with playful attitude. She walks across the studio beneath moving spotlights, lounges briefly on a vintage leather sofa while nodding to the beat, then stands again as industrial fans create natural movement in her ponytail and jacket. The final performance takes place center stage beneath vibrant magenta and blue lights surrounded by drums, LED light bars, chrome speakers, and graffiti walls. She delivers the final lyrics with bold confidence, spins one drumstick in her hand, throws it toward the camera, crosses her arms with a confident smile, and holds a powerful hero pose as the camera slowly pulls back while the lights fade. Style: Premium rap music video, luxury editorial fashion aesthetic, cinematic handheld camera, wide-angle hero shots, smooth gimbal movement, realistic lip-sync, expressive performance, physically accurate lighting, natural fabric simulation, realistic skin texture, shallow depth of field, immersive concert atmosphere, photorealistic, ultra-detailed, 4K HDR, 24fps, 16:9 widescreen. Negative Prompt: No subtitles, no captions, no logos, no watermarks, no duplicate people, no distorted anatomy, no extra fingers, no AI artifacts, no flickering, no low-resolution textures, no cartoon style, no oversaturated colors, no inconsistent outfit or facial features.
- The wardrobe inventory is written jewel-by-jewel, giving the model a checklist that survives fast movement and set changes.
- Camera behavior is choreographed per station (orbits, overheads, low angles at the drums), so coverage varies while identity holds.
- Industrial fans creating hair and jacket movement is a practical trick that adds life to every static pose.
Image1 Identity Lock Morning Brief
A reusable identity template: inherit only the face and hairstyle from Image1, ignore everything else, and play out a groggy morning bathroom routine.
Subject: Person from Image1. Face and hairstyle must match Image1 exactly; do not change identity. Ignore its outfit, background, pose, and text. Outfit: oversized casual sleepwear, messy morning look. 9:16 vertical. Old iPhone everyday-video aesthetic throughout: static phone propped on bathroom sink, standard 1x lens, no distortion, heavy noise/compression, slight mirror steam, warm/off-white overhead lighting. Natural skin, pores, flyaways, under-eye tiredness. No beauty filter, grading, cinematic/CG look, fisheye, vignette, or legible text. 0–4s: Groggy, walks in yawning, glances at phone/mirror, rubs eyes. 4–8s: Brushes messy hair and mutters, “okay... five more minutes wasn't enough.” 8–12s: Steps on bathroom scale, looks down, gives a subtle eye-roll/sigh/shrug, steps off. 12–16s: Opens small closet, holds up two shirts one after another, indecisive. 16–19s: Chooses the first, tosses the other aside, looks at camera and says softly, “…this one. good enough for today,” with a tired smile; freeze final frame. Bathroom clutter: toothpaste/skincare bottles, but all labels illegible. Sound only: bathroom ambience, hairbrush, scale beep/click, fabric rustle, close muffled sleepy voice with slight bathroom reverb. Keep all cuts and actions; no skipped scenes or on-screen text.
- The inherit/ignore split is stated in one line — face and hair from Image1, outfit, background, pose and text explicitly ignored.
- The static propped-phone premise plus heavy noise gives a believable everyday container for testing identity.
- Illegible labels on all bathroom clutter is a precise way to keep set dressing while banning generated text.
Dialogue & Native Audio
Direct spoken lines, ambience, and performance in one generation.
Alien Commander Battlefield Dialogue
A blockbuster battlefield exchange between an alien commander and a soldier, spoken entirely in an invented alien language.
Prompt: Image1 komutan ve lider olan bir uzaylıdır. Image2 ise asker uzaylıdır. komutan askere bir savaş alanında emir veriyor. Karşılıklı diyalog sahnesi. Konuşmalar tamamen uydurma bir uzaylı dilinde olmalı Bir blockbuster filminden bir savaş sahnesi olmalı. Sinematik kamera hareketleri ve açıları kullanmalısın.
- Asking for a fully invented language frees the model from lip-sync accuracy in any real language.
- Two image references are assigned explicit roles — commander and soldier — so the shot-reverse-shot stays consistent.
- Naming the genre (blockbuster war scene) carries the lighting, scale and camera grammar without spelling each out.
2 characters, 2 refsInvented-language dialogueBlockbuster staging
Natural Japanese Slice-of-Life Dialogue
A warm Japanese indie-film conversation between two friends, with speaker-assigned dialogue, restrained acting, and natural synchronized lip movement.
A cinematic Japanese slice-of-life scene.Two young Japanese women (age 20 and 22) are sitting together and chatting happily. They are close friends having a relaxed conversation. Their lips move naturally with synchronized dialogue (accurate lip sync).Scene: a quiet residential street in Japan in the late afternoon. Warm golden sunlight, gentle breeze, peaceful everyday atmosphere.Camera: cinematic Japanese film style composition, medium two-shot, natural framing, slightly handheld camera, slow cinematic movement.Lighting: soft natural sunlight, realistic skin tones, subtle film color grading.Visual style: Japanese indie film aesthetics, shallow depth of field, soft background blur, realistic acting.Dialogue (spoken in Japanese, natural lip sync):Woman 1: 「今日ほんとうにあたたかいね。春って感じしない？」Woman 2: 「うん、こういう日に外で話すの気持ちいいよね。」Woman 1: 「最近どう？大学はいそがしい？」Woman 2: 「ちょっといそがしいけど、こうやって話すと元気出る。」They smile, laugh lightly, and continue their casual conversation.Ultra realistic, cinematic storytelling, natural acting, 4K film look.
- Each line is assigned to a speaker, reducing ambiguity in voice and lip-sync timing.
- The medium two-shot and restrained camera movement support a quiet conversation instead of competing with it.
- Lighting, acting, and background detail all reinforce the same everyday indie-film tone.
Speaker-assigned linesRestrained actingWarm indie tone
Spanish Podcast Interview with Voice IDs
A Spanish-language podcast interview where each speaker's voice is bound to a specific voice reference ID.
El entrevistador esta en su podcast entrevistando a @8993a3ce-444a-414b-9800-6798a9c997eb y le pregunta con su voz @0949c9e6-24ae-4895-b567-94aa844e0150: " Buenas mi gente, tenemos un nuevo modelo de IA y hemos traido a un experto en ello, Nabil cuentanos" y entonces el invitado dice con su voz @8993a3ce-444a-414b-9800-6798a9c997eb: "Buenas jordi, la verdad que es una cosa de locos. Gracias a este modelo puedo hacer cosas como esta" y se levanta chasquea los dedos y le sale pelo. Se sienta y dice con su voz @7ac71528-ba91-42ec-92e1-89875ed6e49f: "inténtalo tú" y jordi se levanta y chasquea los dedos y entra un equipo de rugby en el podcast y nabil y jordi empiezan a empujarse con el equipo entero como en una pelea. De repente la camara enfoca a nabil en medio de la pelea y este con su voz @7ac71528-ba91-42ec-92e1-89875ed6e49fdice :" Esto solo es posible con el nuevo modelo de seedance, que loco!" y le da un empujon al que tiene encima forcejeando. De repente jordi en medio de la pelea grita con su voz @0949c9e6-24ae-4895-b567-94aa844e0150: "STOP" y todos los de rugby se convierten en plumas que caen al suelo. Jordi y Nabil se miran y les entra un ataque de risa
- Binding each line to a voice ID keeps the two speakers audibly distinct through the whole exchange.
- Podcast framing is a naturally static setup, so the model can spend everything on speech quality.
- Writing the dialogue out in full gives lip-sync an exact target in the target language.
Voices bound to voice IDsTwo-speaker interviewNative Spanish
Sea Otter Nature Documentary with Narration
A BBC-style kelp forest documentary about a mother sea otter and her pup, with warm voiceover narration written into the timeline.
30 seconds, 16:9, BBC Planet Earth nature documentary style, 8K ultra-realistic wildlife cinematography. Morning sunbeams pierce mist above a calm Pacific kelp cove. A mother sea otter floats peacefully on her back in emerald water, wrapped in bull-kelp leaves, while her tiny fluffy 2-week-old pup sleeps safely on her chest. Natural telephoto optics, 200mm lens, shallow depth of field, crystal water sparkles. 0:00-0:06: Low water-level telephoto tracking shot. Sunlight catches droplets on the mother's dark wet fur as she gently licks her pup's head. The pup stretches its tiny paws and lets out a soft squeak. NARRATION (warm, gentle documentary voiceover): "Here, in the quiet shelter of the kelp forest, morning begins with a mother's embrace." 0:06-0:12: Close-up on the pup yawning, its pink tongue visible, fluffing its dense cream-colored chest fur with tiny paws. The mother uses her paws to anchor them to a golden kelp frond. NARRATION: "For this two-week-old pup, her mother's chest is the safest island in the vast ocean." 0:12-0:18: Gentle 90-degree floating orbit around the otters. Golden light-caustics dance across the clear emerald water beneath them. A gentle swell lifts them softly. NARRATION: "Together, wrapped in living kelp, they ride the gentle rhythm of the sea." 0:18-0:24: Tight macro shot on the pup nuzzling the mother's cheek. The mother wraps both forepaws around her pup, closing her eyes in serene contentment. NARRATION: "A bond forged in warmth, drift, and quiet devotion." 0:24-0:30: Slow crane rise upward revealing the full sunlit kelp cove, distant pine-covered cliffs in soft morning fog, the otter pair reduced to a cozy center-frame focal point. NARRATION: "Another peaceful day dawns in the kelp kingdom." SOUND: Soft ocean lap, gentle splash, tiny otter pup squeak, mother's breathing, kelp rustle, warm British documentary narration. LOCKS: Natural fur physics, realistic water dynamics, no human objects, stable horizon, professional wildlife color grading. NEGATIVE: No captions, text, logos, watermark, background music, cartoon eyes, exaggerated color saturation, extra animals.
- The narration is written as scripted lines at specific timecodes, so the voice lands with the matching image.
- Naming a real optical setup — 200mm telephoto, shallow depth of field — reproduces the compressed look of wildlife filming.
- A single calm location keeps the model from cutting away, which is what makes the documentary tone hold.
BBC-style narrationMother otter & pupWarm voiceover
Flower Passing Thank You
A live-action montage where a single flower is passed around the world and each person says "thank you" in their own language.
Live-action style, fast editing, cinematic, 4K, 24fps, warm natural light, real human performance, natural lip-sync, no subtitles. The passing of a single flower serves as the core visual thread for the whole video, the flower passing quickly from one country to the next, linking different regions and people around the globe. In each scene, a character receives the flower, shows a sincere smile, and says "thank you" in their local language. The overall pacing is light and fluid, the camera full of motion, emphasizing a real street/life vibe, warm cross-cultural connection, and the passing of goodwill between people. Transition method: the previous character passes the flower out of frame, and in the next shot another character catches the flower in a new scene; or use a fast whip pan, motion blur, or foreground occlusion to complete a seamless transition; keep the flower visually continuous in frame, forming a "one-take around the world" feeling. Camera style: handheld tracking, slight camera shake, fast push-pull, a mix of close-up and medium shots, real ambient sound atmosphere, cinematic street-shooting quality. The background music is warm, light, with a sense of world travel, gently fading out at the end. Scene 1 [reference image 1] Inside a Chinese flower shop, a real, life-like scene. A girl receives a rose, looks at the camera and smiles, saying naturally: "谢谢！" The camera follows the flower handed in from the right of frame, the girl gently lifting the bouquet after receiving it. Scene 2 [reference image 2] An English street, chilly weather, the streetscape natural. A gentleman receives a carnation, smiles and nods, saying: "Thank you!" Through a whip-pan transition, the flower whips in from the previous scene. Scene 3 [reference image 3] A Mexican market, richly colored, full of bustling life. An auntie receives a bunch of marigolds, presses her palms together, and warmly says: "¡Gracias!" The camera sweeps quickly past the stalls and crowd, freezing on the moment of receiving the flower. Scene 4 [reference image 4] An Indonesian village, natural sunlight pouring down. A child receives a frangipani flower, smiles happily, bows slightly, and says: "Terima kasih!" The camera carries a bit of a running feel, the atmosphere pure and natural. Scene 5 [reference image 5] A Thai street, lively and bustling. A vendor receives a string of jasmine garlands, presses palms together, and warmly says: "ขอบคุณค่ะ!" The camera pushes in lightly, the garland swaying gently in the sunlight. Scene 6 [reference image 6] An Arab courtyard, the light soft, the setting elegant. A lady receives a desert rose, touches her chest and smiles, saying: "شكراً!" The image is quiet and warm, the character's expression sincere. Scene 7 [reference image 7] A Brazilian community, the atmosphere warm and vivid. A boy receives a gerbera daisy, very happy, saying: "Obrigado!" The camera is full of rhythm and life. Scene 8 [reference image 8] A Japanese street, an office worker receives a small flower on a bento box, bows politely, and says: "ありがとう！" The camera is short and crisp, keeping the urban rhythm. Scene 9 [reference image 9] A Korean street, a modern urban feel. A young woman receives an azalea flower, naturally clasps her hands together, and smiles saying: "감사합니다!" The camera lingers briefly on the moment of her smile, then the image softly fades out.
- A single passed flower as a match-cut thread turns nine scenes into one global journey.
- Authentic local language and gesture in each scene makes the cross-cultural warmth feel genuine.
- Whip pans and foreground occlusion keep the transitions seamless and energetic.
Multilingual Office Mystery Comedy
A 30-second 3D office comedy with English, Spanish, and French dialogue, locked character designs, precise lip sync, and beat-by-beat audio direction.
High-quality 3D animated cartoon, stylized modern family-animation film look, oversized heads, huge expressive eyes, exaggerated proportions, smooth rounded clay-like 3D surfaces, subsurface scattering skin, vibrant saturated colors, warm cinematic animated lighting. NOT realistic, NOT live action. 30 seconds, snappy comedic pacing. LOCATION: a bright office break room, cheerful cartoon kitchen counter, a small round table, an open fridge door behind them. On the table sits a white plate holding nothing but crumbs and a smear of chocolate frosting. CHARACTERS (locked, no drift): MAYA — woman, oversized round head, curly dark hair, green blazer, huge suspicious eyes, arms folded. Speaks English. DIEGO — tall skinny man, light blue shirt, enormous eyebrows, very dramatic hand gestures. Speaks Spanish. LUC — short round man, grey knit sweater, sweet innocent face, a tiny smear of chocolate frosting on his cheek that he never notices. Speaks French. COLOR 60:30:10 — 60% bright clean office whites and warm wood / 30% soft mint-green wall / 10% accent of Maya's green blazer and the chocolate frosting. 0–4s: wide shot. All three stand around the table staring down at the empty plate in dramatic silence. Slow push-in on the crumbs like a crime scene. Tense low strings. 4–8s: MAYA leans in, eyes narrowing, and says in English: "Okay. Which one of you ate the last slice?" Cut to her suspicious glare. 8–13s: DIEGO throws both hands up theatrically, offended, and says in Spanish: "¿Yo? ¡Yo ni siquiera como azúcar!" He clutches his chest, scandalised. 13–18s: LUC blinks innocently, shrugs with total sincerity, and says in French: "Moi non plus. Je suis complètement innocent." The frosting is clearly visible on his cheek. Diego slowly turns and stares at him. 18–23s: MAYA points at Luc's face without a word. Beat of silence. LUC touches his cheek, looks at his finger, and freezes, eyes going enormous. 23–27s: LUC, quietly, in French: "...Bon. J'ai peut-être goûté un petit morceau." Maya and Diego both explode in overlapping outrage. 27–30s: Luc slowly licks the frosting off his finger anyway, completely unrepentant, as the other two throw their arms up. Freeze on his guilty little smile. CAMERA: slow push-in on the plate, then natural shot-reverse-shot coverage cutting to whoever speaks, a wide two-shot on the accusation, tight close-up on Luc's frozen face, wide comedic final shot on all three. AUDIO: tense low comedic strings during the standoff, a dramatic sting on Maya's question, cartoon gasp from Diego, dead silence during the pointing beat, overlapping outraged shouting at the end, one cheeky little xylophone note on the final lick. Each character's lips match their own line and language precisely. No background music over the dialogue. FORBIDDEN: no auto-generated subtitles, no background music bed, no voice crossing to the wrong character, no design drift, no realistic or live-action rendering, no named studio references, no readable text or logos.
- Each character has a locked visual design, language, and speaking role.
- The timeline separates dialogue beats, silent reactions, and overlapping audio.
- Explicit forbidden behaviors target common multilingual lip-sync and subtitle failures.
5-Second Japanese Dialogue Drama
A compact Japanese prompt for a five-second two-person dialogue scene, useful for testing whether a simple script can produce clear role assignment and lip sync.
5秒ドラマで日本人の可愛い女性と男性が喋っている動画をください。 女性セリフ「こんにちは！今日はどんな要件で？」 男性セリフ「要件なんてない！君が好きだ！」
- The prompt is short but assigns each line to a named speaking role.
- A five-second duration keeps the test focused on dialogue delivery and lip sync.
- It offers a useful contrast to the long, production-style prompts elsewhere in the library.
Retro Spaceship Captain Monologue
A captain walks his cream-and-chrome ship delivering a reflective monologue in a specified accent, shot in slow deliberate 1970s sci-fi style.
Style: cinematic retro sci-fi, inspired by grand 1970s/80s space films, practical effects, symmetrical compositions, slow deliberate camera movement, cream-and-chrome spaceship interiors, big buttons, glowing panels, analog readouts, subtle film grain, soft haze, dramatic but thoughtful mood. Captain HaHaa has charm, swagger, and warmth. He walks through his ship while delivering a reflective monologue in a confident Australian accent. The tone is philosophical but grounded, ending hopeful and personal. SHOT 1 - 0:00-0:05 Visual: Wide symmetrical shot of a long cream-and-chrome spaceship corridor with glowing wall panels, blinking buttons, and retro consoles built into the walls. Captain HaHaa walks slowly toward camera from the far end, hands loosely behind his back at first, calm and reflective. Camera: Slow centered dolly backward, very smooth, stately and elegant. Dialogue: “Well, here we are, mates, a brand-new age.” SHOT 2 - 0:05-0:10 Visual: Side-profile tracking shot as Captain walks past a row of large retro computer stations, reel-to-reel style panels, switches, and glowing instrument clusters. He lightly brushes a hand across the edge of a chrome console as he passes. Soft practical reflections shimmer across his black uniform and silver trim. Camera: Lateral tracking shot, smooth and measured. Dialogue: “Longer models, bigger worlds, and enough artificial intelligence to make the universe feel rather small.” SHOT 3 - 0:10-0:15 Visual: Captain stops at a large observation window or glowing circular display. He looks out thoughtfully, half in silhouette, ship lights glowing behind him. This should feel like a classic contemplative sci-fi image. He turns slightly back toward camera with a knowing expression. Camera: Medium-wide, slow push in from behind and to the side. Dialogue: “But don’t get too dazzled. Without a proper story, all that power is just pretty lights doing tricks in the dark.” SHOT 4 - 0:15-0:20 Visual: Medium close-up as Captain resumes walking, now moving through a control room doorway with large blinking panels and oversized buttons in the foreground. He points lightly toward camera as he talks, casual and assured, like he’s sharing hard-earned wisdom. Camera: Front-facing tracking medium close-up, slight handheld softness but still controlled. Dialogue: “A machine can build the world… but it can’t tell us why we should care about it.” SHOT 5 - 0:20-0:25 Visual: Captain enters the main bridge in a low-angle hero shot. The bridge is spacious, practical, and beautifully retro: cream consoles, chrome rails, oversized lit buttons, glowing instrument panels, and soft haze in the air. As he steps through the doorway, Fishman Mike and Ron are already there waiting for him near their stations. They both look toward him and give him a friendly thumbs up. Captain gives a small acknowledging grin as he keeps moving forward. After the thumbs up, Fishman Mike and Ron turn and begin working at the bridge controls in the background, adding life and movement behind him. Camera: Low-angle slow push in, slightly epic, widening just enough to include Fishman Mike and Ron in the bridge space. Dialogue: “That’s our job.” “And right now, when almost anything can be made, the rarest thing you can bring to it is yourself.” SHOT 6 - 0:25-0:30 Visual: Tight medium close-up of Captain HaHaa near or beside the captain’s chair as he finishes his speech. Behind him, slightly out of focus, Fishman Mike and Ron continue working at their stations, pressing buttons, checking readouts, and moving with purpose. The bridge feels alive but never distracts from Captain. He leans toward camera slightly with a cheeky half-smile, warm eyes, full Captain HaHaa charisma. Camera: Subtle push in, intimate and strong, with shallow depth of field so Captain stays dominant while Mike and Ron remain visible in the background. Dialogue: “So be weird. Be honest. Make the thing only you would make.” “What a bloody good time to be alive.”
- Naming the accent and the emotional arc of the monologue gives the model a performance target, not just lines.
- Practical-effects vocabulary — big buttons, analog readouts, film grain — keeps the ship from looking like modern CGI.
- Slow deliberate camera movement leaves room for speech, which is what makes a 30-second monologue land.
Arena Duel Countdown Upset
A short beat-by-beat arena fight where a referee counts down aloud and the match ends on a single shocking kick.
(0-4s) Wide shot of the duel arena — the musculer man and the old kung fu master face off, crowd murmuring in anticipation. Referee raises hand and starts counting down: eng::**"3... 2... 1..."**. (4-7s) Referee shouts "Go!" / gives the start signal. The kung fu master bows slightly. (7-9s) Right as the master bows, the musculer man swings his leg and kicks him straight in the head. The master collapses. The entire crowd gasps in shock, frozen in disbelief. (11-15s) The musculer man **English**: "I thought the fight started, why is this old man bowing?" @dreamina_ai #DreaminaCPP
- The spoken countdown is written as literal quoted lines, giving the audio an exact cue to hit.
- One reversal — the kick during a bow — carries the entire clip, so nothing else needs elaboration.
- Crowd reaction is scheduled as its own beat, which is what sells the upset.
Kung Fu Battle with Ambient Audio Only
A 21:9 martial arts fight where the audio brief bans music and dialogue outright, leaving breath, footsteps, cloth and impacts.
# Seedance 2.5 — 30-second Kung Fu Battle Duration: 30 seconds Aspect ratio: 21:9 Format: photorealistic live-action martial arts feature film Audio: environmental sound, breathing, footsteps, cloth movement and impacts only. No BGM, dialogue, subtitles, text, logo or watermark. REFERENCE LOCK Use only the two attached character references. LIN: keep exactly the same face, youthful appearance, twin-bun hairstyle, red ribbons, white hoodie, red jacket with gold dragon embroidery, black pants, shoes, body proportions and colors. MASTER RYU: keep exactly the same elderly face, white eyebrows, long white beard, white hair, martial-arts robe, belt, pants, shoes, body proportions and colors. Preserve both identities, costumes and proportions from the first frame to the last. No redesign, no additional people, no duplication, no face changes, no costume changes. LOCATION AND LOOK Ancient Chinese mountain temple courtyard at sunrise. Weathered stone paving, dark wooden temple buildings, stone lanterns, pine trees, thin morning mist and soft sunlight cutting through branches. Restrained saturation, deep blacks, warm highlights, realistic skin, fabric, dust and debris. The atmosphere is grounded and dramatic, like a premium live-action period action film. No fantasy energy, wire-fu, anime effects or supernatural movement. ACTION LANGUAGE The fight uses physically achievable Hong Kong-style kung fu choreography: fast continuous combinations, precise timing, close-range trapping, redirection of force, environmental awareness, comic-free seriousness, visible weight transfer and clean balance recovery. Every movement must connect logically to the next. No repeated animation, impossible flips, floating, sliding feet or empty air punches. Lin fights with youthful aggression, speed and large committed attacks. Her expression moves from confidence to frustration and fierce concentration. Ryu fights with calm economy. He avoids attacks by centimeters, uses tiny shifts, circular footwork, wrist control, hip rotation and redirection rather than brute force. His expression remains composed. CAMERA Professional long-take choreography with invisible cuts. Mostly 35–40 mm lens. Smooth Steadicam tracking, lateral movement, controlled orbits and brief low-angle inserts. Keep screen direction and spatial geography clear. Both fighters must remain readable. Use close-ups only for decisive moments. No random zoom, excessive shake or disorienting cuts. TIMELINE 0–4 sec Wide shot. Lin and Ryu face each other six meters apart in the misty courtyard. Wind moves ribbons, hair and robes. The camera slowly pushes in. Lin lowers her center of gravity; Ryu remains relaxed. 4–8 sec Lin bursts forward. Dust kicks up under her shoes. She opens with a straight punch, palm strike and low sweep. Ryu slips each attack with minimal head, shoulder and waist movement. The camera tracks beside them, preserving both bodies in frame. 8–13 sec Lin continues without pause: spinning backfist, elbow, high roundhouse kick, landing step and rapid chain punches. Ryu parries once, redirects twice and evades the rest by centimeters. The camera performs a smooth half-orbit, keeping the temple axis and screen direction consistent. 13–18 sec Lin uses the environment. She steps onto a low stone bench, rebounds into a flying side kick, lands on the paving and immediately transitions into a spinning heel kick. Ryu ducks, turns and guides her momentum past him with one hand. The bench remains intact. Dust and fabric react naturally. 18–23 sec Close-range exchange. Lin attacks with elbows, short punches, knee feints and a foot sweep. Ryu traps her wrist, releases, checks her elbow, pivots behind her line and taps her shoulder to disrupt balance. Lin recovers instantly and attacks again. The action is extremely fast but readable, with no pauses or repeated motions. 23–27 sec The fastest section. Lin throws a final relentless combination: body punch, palm, backfist, spinning kick and rising knee. Ryu answers with compact deflections, one low kick to break rhythm and one palm to redirect her center. Heavy impacts produce realistic cloth snaps, foot sounds and small stone fragments. 27–30 sec Lin commits to a powerful descending axe kick. At the last possible instant, Ryu steps inside, turns his hips and redirects her centerline with a precise palm. Lin lands safely, slides one meter and regains balance. Both stop. Dust settles. Leaves drift between them. They hold eye contact with silent mutual respect as the camera cranes backward to reveal the temple and mountains. QUALITY CONTROL Feature-film anatomy and physics. Correct hands and feet. No extra limbs, morphing, flicker, costume drift, face drift, body penetration, object popping, teleportation or environment changes. Maintain consistent lighting, direction, identities and wardrobe throughout.
- The audio section is written as an allow-list, so nothing sneaks in over the fight.
- Reference lock is limited to two characters, keeping the cast closed for the whole sequence.
- Removing music forces the edit to find rhythm in the impacts themselves.
Midnight Laundromat Short Film
A titled 30-second short set in a rain-soaked midnight laundromat, with synchronised dialogue, environmental sound and original music.
Create a 30 second cinematic short film titled The Suit Was Still Listening, presented in 16:9 with synchronized dialogue, environmental sound, and original music. The film must feel completely live action, physically grounded, and captured on location, never glossy or synthetic. Visual language: a rain soaked neighborhood laundromat at midnight, warm amber fluorescent tubes inside, cold blue street light and moving car reflections outside, wet pavement, fogged windows, chipped enamel machines, baskets, detergent boxes, loose receipts, realistic skin texture, natural eye moisture, subtle fabric lint, imperfect hair, restrained film grain, gentle halation, lifted shadows, rich but believable color. Wardrobe creates bold editorial color blocking: Mara wears a cobalt trench over a cream blouse, Noah wears a rust knit polo, the teenage attendant wears faded green workwear, and an elderly customer wears a pale gray suit and dark hat. Use expressive medium close shots, tactile inserts, occasional low angles, clean profile compositions, and brief handheld movement that feels operated by a human. Preserve consistent faces, clothing, props, screen direction, reflections, hand anatomy, and spatial continuity. Use realistic speech timing, breathing, blinking, eye focus, and precise lip synchronization. 0 to 3 seconds. Exterior wide shot through falling rain. A lonely laundromat glows on a dark corner. A black sedan turns slowly into the street. Camera makes a subtle forward creep. Music begins with muted upright bass, brushed snare, a low analog pulse, and the rhythmic churn of washers. 3 to 6 seconds. Interior macro shot through a round washer door. A red scarf turns through soap and water. Cut to Mara opening a dryer. A tiny black transmitter falls from the lining of a cream suit and strikes the tile with a sharp metallic click. The score briefly drops out. 6 to 10 seconds. Low medium two shot. Noah freezes beside a folding table. He says quietly, You said clean the suit. Mara studies the transmitter in her palm and replies, I did. You hid a heartbeat in the lining. Keep the delivery controlled and intimate, not theatrical. 10 to 14 seconds. Tight insert on the teenage attendant checking an old signal meter beside the change machine. A green needle jumps. He looks toward the fogged front window and says, It is still transmitting. Camera racks focus from the meter to white headlights sliding across the glass. 14 to 18 seconds. The sedan stops outside. The elderly customer continues folding a shirt without looking up. He says, Then he is already here. Hold on Mara as the moving headlights carve across her face. Let silence, rain, and machine motors carry the tension. 18 to 22 seconds. Noah whispers, Back door. The old man calmly turns the deadbolt on the back exit and answers, Too obvious. Mara notices a delivery rider outside pushing a rolling laundry cart past the window. Use a fast sequence of close shots: her eyes, the transmitter, the cart wheel, the sedan mirror. 22 to 27 seconds. Mara crosses naturally behind a row of machines, slips the transmitter into a sealed laundry bag on the moving cart through an open service hatch, and returns without drawing attention. Noah asks, What did you do. Mara watches the cart continue down the wet street and says, Gave him a cleaner story. 27 to 30 seconds. Exterior telephoto view. The black sedan pulls away and follows the cart. Cut back inside to a symmetrical medium shot of the four characters framed by spinning washer doors. The red scarf circles behind Mara like a slow warning light. She sits opposite Noah and says, Now tell me who owns the suit. End on the transmitter signal fading from the attendant meter as the final bass note lands. Sound design must include rain on glass, distant tires on wet road, washer motors, dryer buttons, fabric movement, the transmitter click, door lock, fluorescent hum, and soft room reflections around every voice. Dialogue must remain clean and naturally mixed above the music. Avoid visual distortion, artificial camera acceleration, floating objects, excessive shallow focus, oversharpening, plastic skin, extra fingers, unreadable signage, random background motion, or dreamlike effects.
- Giving the film a title focuses the model on a single dramatic idea rather than a series of images.
- Warm interior fluorescents against cold street light gives the location a built-in colour contrast.
- Requesting captured on location, never glossy sets the production register for both image and sound.
Ghost Story Voiceover Visualization
A talking-head anecdote that cuts to voiceover-only while the model visualizes each described room, then returns for the punchline.
Use [image1] as the start of the video. She is speaking to an unseen person off camera. She says: "So I go to see this flat. Top floor, rent's half what it should be, and the agent won't come up the stairs with me." Then cut to the voice only of the woman from [image1] as she continues to talk as a voiceover only. As she talks, her words are visualised as a story in the same visual style. The voiceover is: "First room: shoes. Hundreds of pairs, all facing the door, laces done up. Second room's got rain in it. Indoor rain, proper raincloud pouring raindrops all over the carpet. Third room, there's a window looking out onto a beach in full summer. It was February." Illustrate the voiceover sequence to tell the story visually. Then cut back to [image1] and she says with a smile: "Anyway. I signed the lease that afternoon."
- The on-camera / voiceover / on-camera sandwich is a real editorial structure, and the prompt states each transition explicitly.
- Each visualized room is one concrete image (shoes facing the door, indoor rain, a summer window), so the montage stays legible.
- The deadpan punchline reframes the whole story, proving short dialogue can carry structure, not just flavor.
Bedroom Surveillance Paranormal Night
A static infrared bedroom camera catches a child in the doorway, a whispered exchange, and an unseen presence sitting on the mattress.
Ultra-realistic found-footage paranormal home video aesthetic. Static bedroom surveillance camera mounted high in the corner, slight fisheye distortion, infrared night vision, compressed digital texture, low-light noise, subtle timestamp feel, realistic darkness, quiet room tone, no modern cinematic polish. Authentic paranormal home-video realism, believable sleep behavior, subtle supernatural motion, clean dialogue, stable continuity, unnerving pacing, realistic night-vision texture, viral horror payoff, no gore, no graphic harm. Two sleeping parents in bed. One young child, small silhouette, pale pajamas, quiet, expression unreadable, calm but unsettling. No injury, no gore, only eerie paranormal tension. Ordinary parents’ bedroom at night: double bed, hallway door slightly open, closet, dresser, baby monitor, weak moonlight bleeding through curtains. 0-4s: Locked-off wide surveillance angle - The parents sleep motionless. The room is silent except for a faint fan hum. The bedroom door slowly creaks wider on its own. 4-8s: The child appears silently in the doorway, perfectly still, staring into the room. One parent shifts in sleep but does not wake. A subtle distortion flickers across the frame. 8-12s: The mother wakes slightly and whispers: “Sweetie… what are you doing awake?” The child answers softly, without emotion: “He told me not to wake you.” 12-16s: A visible depression slowly forms on the empty side of the mattress as if someone unseen just sat down. The father jolts awake. The closet door eases open by itself. The child remains frozen in the doorway. 16-20s: The mother turns toward the child, terrified, and asks: “Who told you that?” The child tilts their head and says quietly: “The man behind you.” At that exact moment the camera glitches hard for one second, the parents spin around, and when the image stabilizes the doorway is empty.
- The locked surveillance angle turns a limitation into dread — everything must happen inside one unblinking frame.
- Horror escalates through small physical events (a door creak, a mattress depression) rather than shown monsters.
- The child’s two lines carry the entire payoff; the glitch at the reveal hides the impossible moment.
30s Stories & One Take
Plan a complete progression — hook, development, escalation, payoff — with room to cut.
Six Rooms One Take
A 30-second one-take that follows a man in a black coat through six connected rooms, each a different mood, genre, and lighting world.
One take, the camera smoothly follows a man in a black coat (see [reference image 1]) walking left to right through six connected rooms with different tones and atmospheres. Each room has the same structure: white walls, light-colored herringbone wood floor, French double floor-to-ceiling windows, white sheer curtains, see [reference image 2], but the view outside the window and the indoor atmosphere are completely different. The protagonist walks at a constant speed throughout, passing through each open door in the walls. 0-5s, the first room, themed as an American-comic fight scene; the protagonist enters and fights a character ([reference image 3]), who is defeated. 5-10s, the second room, themed warm, felt style, the window view a sunflower field ([reference image 4]), the indoor light a warm orange soft glow, with a painter painting sunflowers ([reference image 5]). After entering, the protagonist also turns into felt style. 10-15s, the third room, themed sad, the whole image a black-and-white comic stop-motion style, rainy outside the window, the indoor light cold gray and low, a person sitting alone in the center of an empty room on the floor, head down hugging their knees, beside them a phone glowing with an unanswered call screen. After entering the room, the protagonist turns off the room light, then immediately turns it on, the room becoming colorful, instantly growing full of flowers. 15-20s, the fourth room, themed joyful, the whole scene a room submerged in the sea, see [reference image 6], the protagonist swims into the room, beautiful coral reefs and fish schools beside him. 20-25s, the fifth room, themed surprise, the window view a night sky full of fireworks, see [reference image 7], the indoor light flickering with colored reflections, the protagonist swept up in the cheering atmosphere. 25-30s, finally the protagonist arrives in a blank room, stands in the center and snaps his fingers, with a finger-snap sound effect, the whole image goes black, and "seedance" appears in the middle, see [reference image 8]. Overall cinematic quality, high-end fashion-ad style, the light entirely determined by the scene outside the window to form strong emotional contrast, no text in the image.
- One constant-speed walk through six doors gives the model a clear spine for a true one-take.
- Each room swaps style, mood, and lighting, showcasing dramatic range within a single shot.
- Reference frames lock the protagonist and room template so the transformations stay consistent.
8 reference assetsSix rooms, one take30s continuous
Lonely Woman Market One-Shot
A 26-second one-take following a lonely European woman through a teeming market as day, night, and seasons shift within the shot.
Core directive: a full 26-second one-shot narrative short, steady tracking, see [reference video 1], interwoven with smooth orbiting camera moves, see [reference video 2]. A smooth sense of forward motion. Within the single shot, day-and-night alternation and the change of the four seasons occur. The protagonist is a European woman [reference image 1], set amid a sea of people full of bustling life, highlighting an extreme sense of loneliness and cinematographic quality. Segmented camera moves and scene descriptions: 0-3s (steady back-follow): An old wooden door [reference image 2] creaks open, the camera following close behind the back of the European woman wearing [reference image 3] as she steps out. She pauses briefly at the threshold, the light and shadow of the street ahead dappled, the cries of vendors and the crowd's noise rushing at her. Her expression detached, she slowly steps forward and melts into the street. 3-6s (back-side tracking): The camera keeps following smoothly as she steps into a crowded morning market, the atmosphere referencing [reference video 3]. Both sides are packed with richly colored fruit stalls and spice shops, a troupe of street jugglers spitting fire dragons, see [reference image 4], the firelight lighting up the crowd, but she looks neither left nor right, walking through at a steady pace. 6-9s (smooth side orbit): The camera begins to orbit smoothly toward the front-side, capturing the protagonist's profile. She passes a noisy butcher's stall [reference image 5], a young mother holding a baby [reference image 6] brushing past her, the baby staring at her curiously, but she only lowers her eyes slightly to avoid the gaze, not pausing at all. 9-12s (front retreating tracking): The camera continues around to directly in front of the protagonist, tracking backward. The crowd ahead suddenly parts to both sides naturally like the parting of the sea, a huge elephant draped in ornate red cloth [reference image 7] striding steadily into frame from the right, taking up most of the image. 12-15s (gap-threading and circling back): At the moment the woman and the elephant are about to collide, the camera deftly slides through the narrow gap between the elephant and the woman, circling back to her back again. The elephant passes by, vast and quiet, mischievous children cheering and chasing it. The elephant bells and laughter are deafening, yet she does not even slow her steps. 15-18s (gradual shift of environment light): As she walks, the light and shadow within the long take shift magically - the harsh high-summer sun instantly softens, a gust of wind sweeps up a sky full of golden leaves [reference image 8], the seasons seamlessly transitioning to late autumn within the same long take. Falling leaves brush her shoulders. 18-21s (360-degree immersive orbit): Ahead suddenly plunges into a grand street celebration [reference image 9]. The air spits out a sky full of streamers and confetti, vendors leaning out to cheer. The camera here unfolds a continuous 360-degree orbiting move, forming an extremely strong visual rupture between the quiet, lonely protagonist and the frenzied surroundings. 21-24s (circling back to the rear-side): When the camera finishes a full circle and returns to her rear-side, the falling streamers have quietly turned into a sky full of snow - winter arrives in an instant [reference image 10]. Pedestrians put up umbrellas or pull on hoods one after another, the woman shivering slightly, turning up her coat collar, her clothing changing to [reference image 11], continuing alone through the snow. 24-26s (slow push-in tracking): As she walks toward the end of the long street, the sky darkens visibly as she moves, day seamlessly sinking into night. The dim yellow streetlights and stall bulbs on both sides light up one by one [reference image 12], vendors packing up their goods, the noise as if slowly absorbed and pulled away by the heavy snow, her steps gradually slowing. The night sky suddenly bursts with a grand display of fireworks [reference image 13], the firework sound referencing [reference audio 1], the colorful light spots flickering and leaping across the building walls and in her eyes. The world is as lively as ever, while she quietly looks up, the camera slowly pulling back, gently closing here.
- Day-night and full-season changes inside one unbroken take are a showcase of temporal control.
- Pinning the lonely protagonist against a frenzied crowd creates strong, consistent emotional contrast.
- A rich mix of image, video, and audio references locks every beat of the complex sequence.
17 reference assetsDay → night → seasons26s one-shot
London Techno Club 30-Second One-Shot
A continuous 30-second journey from an overwhelming London techno club to a quiet street-side ending, with the soundscape changing at every transition.
Original scene, 30 seconds, one continuous shot, no cuts. 0–8 seconds: Inside a packed underground London techno club. The camera holds tightly on the face of a young English woman. She is Caucasian, brunette, with delicate features and melancholy behind her eyes. She remains centered in frame and only sways subtly with the music. Around her, the crowd moves intensely and chaotically, with bodies, arms, shoulders and faces constantly passing close to camera, creating strong motion blur and a sense of pressure and overwhelm. Fast white strobe lights flash continuously, pushing the image back and forth between near-total darkness and sudden bursts of harsh illumination. In the darker intervals, only silhouettes, rim light, glints of sweat and fragmented movement are visible. Each flash briefly reveals fragments of her face—her eyes, cheekbones, wet strands of hair, and distant expression—before she disappears again into darkness. She feels strangely still and emotionally detached while the crowd around her becomes a mass of blurred bodies and flickering light. Heavy four-on-the-floor techno dominates the soundscape, loud, compressed and physically overwhelming. 8–16 seconds: She stays in this space for a moment longer, absorbing the intensity, then finally breaks her gaze, turns and begins pulling herself out of the crowd. The camera does not cut. It releases from the locked close-up and shifts into a close handheld follow shot, staying just behind and slightly beside her as she pushes through dancers. Bodies knock into her shoulders. Arms and backs occasionally obscure the frame. The camera feels intimate, bumped and instinctive, struggling through the same crowded space with her. As she leaves the center of the dancefloor, the strobing becomes less dominant and the club lighting grows dirtier and more practical. She enters a narrow back passage leading away from the main room. 16–23 seconds: She moves through a cramped, dirty corridor with graffiti-covered walls, peeling paint, torn posters, exposed pipes, damp patches, flickering fluorescent lights and littered plastic cups on the floor. People lean against the walls smoking, chatting, waiting, watching others pass. She threads through them silently. The camera stays close and observational, catching the rustle of fabric, brief shoulder contact and bodies slipping past in the narrow space. The music becomes more muffled and distant as she moves farther from the dancefloor. The heavy techno remains present only as a low, dulled throb through the walls. Footsteps, clothing friction, breathing, shuffling bodies and indistinct overlapping crowd chatter become clearer. No individual conversation is intelligible. She does not speak. 23–30 seconds: She pushes through the exit and steps into the cold London night. Outside the club, groups of people stand smoking, talking, drifting in and out of the entrance. Streetlight mixes with spill from the doorway and practical urban light. She walks to the nearest dirty exterior wall and pauses. With slightly shaky hands, she lights a cigarette. The flame briefly illuminates her face. She takes a drag, leans back against the wall, then slowly slides down into a seated position on the pavement. The camera follows her downward and settles at her level, then holds. She sits smoking in silence, looking past the moving crowd into the distance, disconnected from everything around her. People continue crossing the frame, talking, laughing and smoking nearby, but she feels completely alone inside the busy environment. The sound transitions from overwhelming club techno, to muffled bass and corridor ambience, to distant low-frequency vibration outside mixed with cigarette lighter clicks, breathing, street ambience, footsteps and indistinct smoker chatter. No dialogue. The overall image should feel raw, naturalistic and grounded, with visible film grain, slight exposure fluctuation, realistic skin texture and subtle handheld instability. Avoid glossy polish, commercial beauty lighting and music-video slickness.
- The four timeline beats preserve one continuous emotional arc while changing location and camera behavior.
- The sound design transitions with the character, making the move from pressure to isolation easy to feel.
- Foreground occlusion and handheld instability give the one-shot believable physical continuity.
Club → street journeyContinuous 30sSound-led arc
IMAX Tokyo with the Camera as Protagonist
An uninterrupted IMAX-composed action take through a devastated futuristic Tokyo, where the camera itself is declared the protagonist.
A photorealistic live-action 30-second uninterrupted one-shot action sequence, presented in native 16:9 widescreen cinematic format. Designed specifically for a full-width IMAX composition with an epic sense of horizontal scale. Visual quality comparable to a $350 million Hollywood blockbuster. The camera is the true protagonist. A devastated futuristic Tokyo stretches across the horizon. Endless ruined skyscrapers, collapsed highways, burning buildings, thick smoke columns, drifting ash, military helicopters, and distant explosions fill the entire width of the frame. The opening begins with an enormous ultra-wide aerial establishing shot. The camera dives from the clouds toward the ruined city at breathtaking speed before seamlessly transitioning into an aggressive FPV drone flight. A lone samurai in realistic black armor stands in the center of an abandoned avenue. Far in the distance, occupying nearly the entire width of the horizon, a colossal 120-meter stone titan slowly emerges between skyscrapers. The camera never cuts. The titan charges. Every footstep sends shockwaves through multiple city blocks. The camera accelerates violently. It flies between skyscrapers, through broken office floors, underneath collapsing bridges, inches above destroyed streets, then suddenly climbs hundreds of meters before diving again. The camera constantly sweeps horizontally across the city, fully utilizing the 16:9 frame to reveal the immense scale of Tokyo. Buildings rush past both sides of the frame with massive cinematic parallax. The samurai sprints through the destruction. The camera races beside him, then overtakes him, flies backward while tracking his face, performs wide orbit shots, dramatic side tracking shots, sweeping crane movements, low-angle hero shots, extreme wide establishing shots, and breathtaking aerial reveals—all without a single cut. The samurai runs vertically along a collapsing skyscraper. The camera follows only inches behind him before swinging outward into an enormous wide shot, revealing the titan filling almost the entire frame. The camera dives beneath the titan, spirals upward around its massive body, then performs a huge 360-degree orbit as debris, fire, shattered glass, sparks, and smoke explode across the widescreen image. Natural cinematic camera inertia, realistic handheld momentum, subtle vibration from explosions, dynamic focus pulls, anamorphic lens flares, realistic motion blur, volumetric lighting, HDR, atmospheric haze, practical lighting, physically accurate destruction. Silence. The camera slowly pushes toward the samurai. He assumes an iaido stance. An explosive burst of movement. The camera follows the slash in one impossible continuous motion before rapidly pulling back thousands of meters. The titan freezes. A glowing cut slowly appears. The titan splits perfectly in half. Both halves collapse across the entire width of the city, generating an immense wall of dust that rolls across the skyline. The final shot is an ultra-wide aerial pullback revealing the burning ruins of Tokyo stretching from edge to edge of the frame, with the lone samurai reduced to a tiny silhouette in the foreground. Photorealistic live action, IMAX cinematic realism, ultra-detailed environments, massive sense of scale, seamless one-shot, award-winning visual effects, physically believable camera movement, spectacular destruction, emotionally powerful composition, 16:9 optimized, ultra-wide cinematic framing, no text, no subtitles, no watermark. A photorealistic live-action 30-second uninterrupted one-shot action sequence, presented in native 16:9 widescreen cinematic format. Designed specifically for a full-width IMAX composition with an epic sense of horizontal scale. Visual quality comparable to a $350 million Hollywood blockbuster. The camera is the true protagonist. A devastated futuristic Tokyo stretches across the horizon. Endless ruined skyscrapers, collapsed highways, burning buildings, thick smoke columns, drifting ash, military helicopters, and distant explosions fill the entire width of the frame. The opening begins with an enormous ultra-wide aerial establishing shot. The camera dives from the clouds toward the ruined city at breathtaking speed before seamlessly transitioning into an aggressive FPV drone flight. A lone samurai in realistic black armor stands in the center of an abandoned avenue. Far in the distance, occupying nearly the entire width of the horizon, a colossal 120-meter stone titan slowly emerges between skyscrapers. The camera never cuts. The titan charges. Every footstep sends shockwaves through multiple city blocks. The camera accelerates violently. It flies between skyscrapers, through broken office floors, underneath collapsing bridges, inches above destroyed streets, then suddenly climbs hundreds of meters before diving again. The camera constantly sweeps horizontally across the city, fully utilizing the 16:9 frame to reveal the immense scale of Tokyo. Buildings rush past both sides of the frame with massive cinematic parallax. The samurai sprints through the destruction. The camera races beside him, then overtakes him, flies backward while tracking his face, performs wide orbit shots, dramatic side tracking shots, sweeping crane movements, low-angle hero shots, extreme wide establishing shots, and breathtaking aerial reveals—all without a single cut. The samurai runs vertically along a collapsing skyscraper. The camera follows only inches behind him before swinging outward into an enormous wide shot, revealing the titan filling almost the entire frame. The camera dives beneath the titan, spirals upward around its massive body, then performs a huge 360-degree orbit as debris, fire, shattered glass, sparks, and smoke explode across the widescreen image. Natural cinematic camera inertia, realistic handheld momentum, subtle vibration from explosions, dynamic focus pulls, anamorphic lens flares, realistic motion blur, volumetric lighting, HDR, atmospheric haze, practical lighting, physically accurate destruction. Silence. The camera slowly pushes toward the samurai. He assumes an iaido stance. An explosive burst of movement. The camera follows the slash in one impossible continuous motion before rapidly pulling back thousands of meters. The titan freezes. A glowing cut slowly appears. The titan splits perfectly in half. Both halves collapse across the entire width of the city, generating an immense wall of dust that rolls across the skyline. The final shot is an ultra-wide aerial pullback revealing the burning ruins of Tokyo stretching from edge to edge of the frame, with the lone samurai reduced to a tiny silhouette in the foreground. Photorealistic live action, IMAX cinematic realism, ultra-detailed environments, massive sense of scale, seamless one-shot, award-winning visual effects, physically believable camera movement, spectacular destruction, emotionally powerful composition, 16:9 optimized, ultra-wide cinematic framing, no text, no subtitles, no watermark.
- Naming the camera as the true protagonist gives every movement narrative motivation instead of decoration.
- IMAX composition is stated as a framing intent, so the model favours horizontal scale in every beat.
- A single devastated city stretching to the horizon gives the long take a consistent world to traverse.
Camera as protagonistIMAX compositionUninterrupted take
Football 3000-Year History
A 30-second history short where one ball rolls through 3000 years, morphing across civilizations from cuju to the modern game.
Make a 30-second educational short about the 3000-year evolution of football, using the same ball as the visual through-line for the whole film, the ball rolling, traveling, and transforming all the way from ancient times, linking different civilizations and eras. The overall pacing is tight, the imagery high-end, blending historical educational short and artistic transitions, highlighting the feeling of one ball spanning three thousand years, with concise, powerful voiceover. At the opening, an ancient ball slowly emerges from a black background, its surface bearing the texture of age, then rolls into a Warring States cuju scene in China, the image turning into ink-wash style, in the style of [reference image 1], ancients in period costume playing cuju in a courtyard, movements elegant, the ball bouncing at their feet. Voiceover: The football story begins with cuju. Next, the ball keeps rolling forward, the image transitioning naturally to an ancient Greek ball game, the image in classical oil-painting style, style referencing [reference image 2], the plaza and stone columns clearly visible, people in ancient Greek robes playing ball, the image weighty and historical. Voiceover: The Greeks also loved ball games. Then the ball rolls into medieval Europe, the image still in oil-painting style, a village, muddy ground, common folk chasing a leather ball, the atmosphere fervent and rough, like folk football carrying the flame onward. Voiceover: The folk of Europe kept ball games alive. Then the ball is kicked away, the image switching to black-and-white documentary style, see [reference image 3], arriving in 1863 Britain, gentlemen, clubs, and grass pitches gradually appearing, symbolizing the formal birth of modern football, this ball taking on the standard look of a modern football for the first time. Voiceover: In 1863, modern football took shape. Then the image quickly enters the modern era, the ball spinning in the air, bringing out key milestones in turn, lights, stadiums, crowds, trophies, and global scenes interweaving, showing football going from a local sport to a global one. At the end, this ball sits at the center of a modern stadium, crowds and cheers from around the world blending in the background, creating a "one ball connects the world" feeling, the image grand and epic. Voiceover: Today, football connects the whole world.
- One persistent ball as a match-cut anchor turns a sweeping timeline into a single seamless journey.
- Each era gets a distinct art style (ink-wash, oil painting, documentary) referenced from images.
- Tight voiceover beats keep the educational structure clear while transitions stay artistic.
FPV Drone Multilingual Greetings
A 33-second one-take FPV descent where clouds, mist, water, and city light spell "hello" in eleven languages, one per zone.
A one-take FPV drone first-person-view video, a 33-second continuous long take, no cuts, no jump cuts, no transitions. The shot starts inside high-altitude clouds, descending along a continuous flight line through cloud layers, mist, light and shadow, a valley, a waterfall, a lake surface, a flower field, city buildings, and a near-ground plaza. Throughout, 11 distinct independent language display zones appear in sequence, each zone showing only the corresponding single language's text, no mixing, no overlay, no adding other languages. 0-3s, [reference image 1] cloud masses naturally form the Chinese "你好"; 3-6s, [reference image 2] thin mist and volumetric light form the English "Hello"; 6-9s, [reference image 3] high-altitude water vapor and sunlight projection form the Spanish (Mexico) "Hola"; 9-12s, [reference image 4] airborne ribbons form the Indonesian "Halo"; 12-15s, [reference image 5] a kite formation forms the Malay "Hai"; 15-18s, [reference image 6] valley morning mist forms the Thai "สวัสดี"; 18-21s, [reference image 7] waterfall spray forms the Arabic "مرحبا"; 21-24s, [reference image 8] the lake's reflection and ripple light patterns form the Portuguese "Olá"; 24-27s, [reference image 9] a flower field and grassland naturally arrange into the Vietnamese "Xin chào"; 27-30s, [reference image 10] the reflected light and shadow on city glass buildings form the Japanese "こんにちは"; 30-33s, [reference image 11] the fountain spray, ground paving, and light strips of the near-ground plaza form the Korean "안녕하세요". The overall atmosphere is an early-morning sunrise, golden backlight, soft volumetric light, realistic clouds and mist, natural motion blur, cinematic realism. The camera speed starts slowly at 3-5 m/s, gradually accelerating to 14-16 m/s crossing the natural landscape, then decelerating to 2-3 m/s to hover stably at the near-ground plaza. Camera parameters: wide-angle lens, 24fps, smooth FPV drone movement, pitch transitioning gradually from -5° to -18°, finally returning to 0°; slight yaw ±10°, roll kept within 0-10°, ensuring a continuous, stable, realistic one-take flight feel.
- A continuous FPV descent makes a multilingual showcase feel like one breathtaking flight.
- Each greeting forms organically from natural elements (clouds, mist, water) rather than overlaid text.
- Explicit speed and gimbal parameters give the model the control needed for a believable one-take.
Surreal Cloud World POV With Spatial Audio
A first-person journey through an impossible cloud world, combining timestamped story beats, gravity changes, intimate dialogue, and spatial sound design.
immersive surreal cinematic film, hyper-detailed, true-to-life lighting and shadows mixed with impossible physics, rich motion detail, volumetric god rays, anamorphic lenses, subtle film grain, masterpiece quality. Immersive multi-shot story with precise timestamp control and native spatial audio: [0-6s] Extreme first-person POV standing on the edge of a floating cliff made of soft glowing moss. Below is an endless ocean of gigantic, super-fluffy cotton-candy clouds — each cloud the size of a mountain, impossibly soft and billowing like living marshmallows. Soft male voice, calm but trembling: “I’ve dreamed of this place my entire life.” [6-12s] He jumps. Seamless first-person freefall into the giant fluffy clouds. Instead of falling through, he sinks slowly like diving into warm foam. The clouds part and reshape around him into soft tunnels of pink, gold and lavender. Impossible physics: gravity flips gently mid-fall. Soft voice (awed): “They’re soft… they’re alive…” [12-18s] He emerges inside a vast floating world made entirely of living clouds and translucent crystal islands. Giant fluffy cloud whales swim slowly through the sky. Soft glowing staircases of solid mist rise and fall. He lands on a cloud bridge that bounces like a trampoline under his feet. Camera orbits him as the entire sky breathes and shifts colors. [18-25s] He starts running and the cloud bridge launches him into the air. First-person flight through the impossible sky: weaving between mountain-sized fluffy clouds that open like flowers, diving through glowing mist waterfalls that turn into liquid starlight, racing alongside cloud whales that leave trails of sparkling dust. Reality bends — the horizon folds into a spiral. [25-30s] Final wide crane shot as he soars higher and higher until the entire cloud world forms a giant glowing heart shape around him. Soft voice (peaceful, almost whispering): “I was never falling… I was coming home.” Hyper-detailed, breathtaking surreal world-building, perfect motion continuity, emotional story of discovery and belonging, immersive first-person hybrid style, native dual-channel audio (soft wind, distant whale-like hums, ethereal music swell, intimate dialogue), pure dream logic, viral awe factor.
- Each six-second beat introduces one new physical rule without losing the emotional through-line.
- The prompt coordinates first-person motion, a final external crane shot, dialogue, and ambient spatial audio.
- Repeated cloud materials and colors keep the surreal world visually coherent.
Continuous Fall From Orbit to a Raindrop
A one-line prompt that turns a continuous fall from orbit through a storm into a macro landing on one raindrop resting on a leaf.
One continuous fall. Orbit → atmosphere → storm → mountains → forest → one raindrop on a leaf.
- The ordered location chain gives the camera a clear route across extreme changes in scale.
- Repeating one continuous fall keeps the whole transformation tied to a single motion.
- The final raindrop supplies a precise visual payoff instead of ending on a broad landscape.
Backstage-to-Arena Concert One-Shot
A continuous handheld journey that follows a singer from a backstage dressing room through the corridor and onto a packed arena stage.
T2V prompt: One-take handheld gimbal tracking shot. The camera slowly pushes in through a gap in a heavy red curtain and enters a warm-toned backstage dressing room. A young female singer, with her back to the camera, is adjusting her earpiece as a staff member reminds her it's time to go on. She turns toward the camera and starts singing citypop. The camera pulls back and tracks her as she passes through the curtain into a dim backstage corridor, interacting naturally with her dancers along the way; one staff member hands her a microphone. She and the dancers then step onto the stage, and the camera arcs around to the back, gradually revealing the red-and-black stage design, LED screens, spotlights, haze, and reflective floor. The camera finally pulls out to a wide shot of the arena, showing the packed audience, light boards, glow sticks, and cheering crowd, capturing the youthful, free-spirited climax of the concert.
- Curtains, corridors, and the stage entrance act as physical transition anchors for the continuous take.
- Every camera move is paired with a clear subject action, from adjusting the earpiece to taking the microphone.
- The final pullback turns a close backstage opening into a large arena payoff.
Coastal Japan Morning Commute POV
An unbroken first-person walk through a seaside Japanese town at morning, with head bob, hand glances and no color-graded fantasy.
Full prompt: POV — Morning Commute in Coastal Japan | Ultra-Realistic, One Continuous Take First-person POV, no cuts, one unbroken handheld-feeling shot from our own eyes on the way through a small seaside town. Ultra-photorealistic, phone-in-hand realism — natural camera micro-shake, subtle head bob with each step, occasional glance down at our own hands and shoes. 4K, shallow but natural depth of field, real morning light, no color-grading fantasy, no neon. Beat 1 — Descending into the station (0–4s): We walk down worn concrete station stairs into a small coastal-town metro entrance, one hand loosely gripping a canvas bag strap that swings into the lower frame. Fluorescent tint mixes with daylight bleeding from the entrance behind us. Commuters pass in soft focus; we hear muffled announcements and the shuffle of footsteps. Beat 2 — The orange cat (4–9s): We slow and crouch — the horizon dips as our POV lowers toward the ground. An orange tabby sits by a ticket-gate pillar, tail curled. Our hand (natural skin texture, slightly bitten nails, cuff of a sleeve) reaches into frame and gently strokes its head. The cat leans into the touch, eyes half-closing, ears flicking. We hold there a beat, warm and quiet. Beat 3 — Boarding, settling by the window (9–14s): We rise, the horizon lifts, and we step through the train doors just as the chime sounds. POV turns and moves toward a window seat; we sit, and the frame settles against the glass. A faint silhouette of us ghosts over the view. The train pulls away with a gentle lurch. Beat 4 — The shimmering sea (14–20s): Through the window, the town gives way to open coastline. Sunlight scatters across the water in thousands of moving sparkles — real specular glitter, not CGI bloom. Utility poles and wires strobe past in the foreground. We rest our chin lightly (subtle downward frame tilt), just watching. Beat 5 — Rails into the sea (20–25s): The track curves and runs so close to the shore that the rails seem to vanish straight into the water — the sea fills nearly the whole frame, waves lapping right up to the ballast. Foam catches the light. We're gliding along the edge of the ocean, the horizon line steady, gulls crossing in the distance. Hold on this until the shot ends. Technical spec: continuous POV, first-person, no cuts or transitions, natural handheld micro-motion, realistic morning ambient audio (station hum, cat, train chime, rail clatter, distant surf), authentic Japanese coastal-railway setting (Shimonada / Enoden-style seaside line), overcast-to-clear soft daylight, photoreal skin and fabric texture, 2.39:1 or 16:9, ultra-realistic.
- Physical POV tells — micro-shake, head bob per step, glancing at your own hands — are what make first-person read as embodied.
- Banning neon and graded fantasy keeps the look inside real morning light.
- Numbered beats give the walk a route, so the one-take never wanders without purpose.
Epic Fantasy Continuous Long Take
A 30-second photoreal fantasy long take through original worldbuilding, written to avoid any resemblance to existing films or characters.
16:9, 30 seconds, an epic photorealistic fantasy cinematic long take, original worldbuilding, one continuous shot, continuous camera movement, no hard cuts, and no references to any existing film, character, actor, or recognizable cinematic scene. OVERALL STYLE: A high-budget fantasy film aesthetic with realistic cinematography, monumental world scale, and a beautiful protagonist with natural skin, realistic expressions, and believable body proportions. The overall tone is intelligent, elegant, mysterious, and courageous, never childish, cartoonish, or exaggerated cosplay. Four locations are connected through one continuous flight path: Iceland’s black coastline, an alternate Victorian London, a Paris-inspired city at night in the rain, and a futuristic New York-inspired aerial metropolis. UNIFIED COLOR PALETTE: Deep black, silver-gray, and warm gold remain the dominant colors throughout the film. Iceland adds cold blue; London adds gray-green and amber; Paris adds deep blue and wet gold; New York adds deep teal, silver-white, and gold. Maintain realistic atmospheric perspective, thin mist, rainfall, wet surfaces, glass reflections, and volumetric light throughout. Avoid a video-game look, concept-art appearance, and plastic materials. MAIN CHARACTER: There is only one female protagonist throughout the entire video. She is approximately 28 years old, slender, exceptionally beautiful, intelligent, elegant, and quietly determined. Her refined facial features are completely original and must not copy any real actor or movie character. She has naturally bright eyes, clearly defined eyebrows, a soft but strong facial structure, natural skin tone, realistic skin texture, and a restrained, focused expression. She has warm chestnut-brown hair reaching her waist, naturally wavy at the ends. Part of her hair is blown behind her shoulders by the wind. Her hairstyle must remain identical throughout the entire film. She wears a deep forest-green long coat, an ivory high-neck blouse, a dark-red knitted scarf, brown leather wrist guards, dark-gray trousers, and worn leather boots. Her costume has an elevated British fantasy aesthetic, but she does not wear a school uniform or pointed hat. Do not include badges, school emblems, magical-school symbols, recognizable character costumes, or elements from any existing film. She rides the same original flying broom throughout the sequence: a dark, aged wooden handle with silver-gray metallic fibers at the rear and a small warm-gold light at the front. The broom’s shape, size, color, and materials must never change. HER OBJECTIVE: She is flying through different cities to carry the small warm-gold light toward the far edge of the clouds. She is not a combat character. She does not attack anyone or cast explosive magic. She simply continues forward through cities, coastlines, fog, rain, and high-altitude air. Her emotional progression moves from concentration to wonder, then finally to freedom and determination. 0-5 SECONDS: TAKEOFF FROM ICELAND’S BLACK-SAND BEACH The shot begins extremely low above a black volcanic beach using a 24mm wide-angle lens. Black ocean waves are on the left, towering basalt columns on the right, and blue-white glacial mountains in the distance. Cold blue clouds press down across the sky, while a narrow line of warm golden sunset remains near the horizon. The beautiful female traveler rapidly enters from the rear right of the frame, riding her broom just above the ocean surface. Her chestnut-brown hair streams backward in the sea wind. Her dark-red scarf creates a clean motion line behind her, while her deep forest-green coat moves naturally in the airflow. The warm-gold light at the front of the broom illuminates the sea mist and droplets of water. The camera follows her from behind with a stable FPV movement, keeping her slightly right of center. It must not circle around to the front or allow her to leave the frame. Her body leans slightly forward; one hand holds the broom handle while the other maintains balance. She flies toward a massive wall of blue ice. At the fourth second, she enters a natural裂缝 beneath the ice wall. The ice passes rapidly along both sides of the camera. Cold blue crystals briefly intersect with the warm-gold light, creating the first natural transition. No explosion, magical smoke, or sudden transformation. 5-12 SECONDS: VICTORIAN LONDON IN THE FOG As the ice clears the lens, the environment naturally becomes an alternate Victorian city at night. The protagonist and broom retain exactly the same direction, speed, clothing, appearance, and flying posture. The camera continues following from behind. Below are wet dark-gray stone streets. Red-brick buildings, black iron bridges, narrow windows, and old amber streetlamps line both sides. Several dark-red double-decker public vehicles without text or branding move slowly through the fog. The city should evoke Victorian London without reproducing real landmarks. The camera gradually transitions from fast FPV pursuit into a smooth three-quarter rear tracking shot, moving approximately 45 degrees to her left side. Her beautiful profile appears briefly. Her eyes remain focused, and her hair and scarf maintain stable continuity. The warm-gold light leaves only a short trail through the rain and fog. She passes beneath a black elevated iron bridge. Its steel structure moves across the top of the frame as a brief physical occlusion. The camera does not cut, and when the obstruction clears, she remains on the same movement axis. At the tenth second, she flies into a massive arched railway station. Its roof is made from black steel beams and wet glass, with rainwater flowing across the surface. The roof completely covers the frame, creating the second natural transition. 12-19 SECONDS: PARIS-INSPIRED CITY IN THE RAIN When the glass roof clears the camera, the environment becomes a romantic, original Paris-inspired city at night in the rain. Do not reproduce real landmarks. Preserve only the atmosphere of stone bridges, a river, narrow streets, classical stone buildings, wrought-iron balconies, and warm window light. The protagonist flies low above a broad river. The water reflects golden windows and the deep-blue night sky. Pale-gray stone buildings, tall narrow windows, wet rooftops, and fine rain lines extend along both sides. Her deep-green coat and dark-red scarf form a clear silhouette against the blue city, while her chestnut hair streams backward. The camera moves into a parallel tracking position on her right side. The broom stays approximately three meters above the river. The camera remains slightly below shoulder level, preserving the spatial relationship between the woman, broom, river, and architecture. She passes beneath a sequence of classical stone bridges whose arches form continuous reflections in the water. At the seventeenth second, she enters a long mirror corridor made from wet glass walls. The reflections may show only the same woman, the same broom, and the same warm-gold light. Do not create duplicate people. Rainwater, city lights, and reflections slide along the glass surfaces. A powerful warm-gold light appears at the end of the corridor. She flies toward it, creating the third natural transition. 19-24 SECONDS: FUTURISTIC NEW YORK-INSPIRED CITY The mirror corridor opens into an original futuristic New York-inspired metropolis. The camera rapidly but smoothly shifts from the three-quarter rear position into a controlled forward-facing FPV shot moving backward in front of her. Her beautiful, focused face, chestnut hair, dark-red scarf, and the golden broom light are briefly visible. Below are wet streets, glass skyscrapers, metallic elevated bridges, and enormous urban canyons. The buildings reflect golden light, a deep-teal night sky, and silver-white mist. All screens and glass surfaces must remain abstract and free of text, advertisements, logos, or branding. She flies between two skyscrapers. The glass wall on the left passes close to the camera, while a vast urban canyon opens on the right. The camera briefly maintains its backward-facing position before completing one stable 90-degree upward movement, transitioning from her face to a position above her. Do not spin rapidly, make her tumble, or transform the broom into an aircraft. She remains graceful, skilled, and stable. At the twenty-third second, she bursts out from between the skyscrapers. The city lights rapidly become smaller below her, while the warm-gold light at the front of the broom becomes the only stable light source near the center of the image. 24-30 SECONDS: THE FINAL WORLD ABOVE THE CLOUDS The camera continues rising at high speed and passes through a dense layer of cloud. When the clouds clear, the protagonist appears high above a vast cloud sea, hovering on her broom. She gradually slows down and changes from a forward-leaning posture to a more upright position. Her chestnut hair and dark-red scarf move backward in the high-altitude wind. The camera moves from the front to her right rear side, then rises into a high-angle 24mm wide shot. Distant traces of the four worlds appear below without forming a chaotic collage: Iceland’s black coastline and blue glacier on the far left; London-inspired red-brick structures and gray-green fog in the middle distance; Paris-inspired golden waterways and stone bridges on the right; and silver-white lights from the New York-inspired glass city at the lowest level. These locations must exist only as distant spatial layers. Do not suddenly reproduce four complete cities or make buildings float and reorganize. A warm golden horizon appears at the edge of the clouds, suggesting that another world is waiting beyond it. At the twenty-eighth second, the protagonist raises her right hand. The warm-gold light at the front of the broom emits one thin beam toward the horizon. The beam only illuminates a new path through the clouds. It does not explode, create a giant energy sphere, or alter her appearance. During seconds twenty-nine to thirty, the camera becomes completely stable. The protagonist, broom, cloud sea, distant layers of the four cities, and golden horizon are all clearly visible. She appears as a beautiful but small figure near the lower center of the frame, facing the open world. The final emotion is freedom, wonder, and the sense that the journey will continue. CAMERA AND PACING: 0-5 seconds: low-altitude rear FPV pursuit. 5-12 seconds: smooth three-quarter rear tracking through London. 12-19 seconds: parallel low-altitude tracking through Paris. 19-24 seconds: one controlled front-facing backward FPV movement through New York. 24-30 seconds: continuous rise into a high-angle wide establishing shot. Use FPV speed only during the Iceland takeoff and New York skyscraper passage. Keep the London and Paris sections controlled, elegant, and spatially readable. SOUND DESIGN: Iceland: ocean waves, cold wind, low glacial rumbling, and subtle vibration from the wooden broom. London: rain, steam, iron-bridge resonance, and distant wheels. Paris: rain droplets, water, distant bells, and low strings. New York: low urban rumble, wind pressure across glass, and metallic structural resonance. Above the clouds, all city sounds gradually fade, leaving high-altitude wind, a subtle metallic resonance from the broom fibers, and one warm sustained string note. CONTINUITY RESTRICTIONS: Only one female protagonist appears throughout the video. She must remain exceptionally beautiful, natural, and realistic, with stable original facial features that do not copy any actor or film character. Her chestnut-brown hair must retain the same color, length, and hairstyle. Her forest-green coat, ivory blouse, dark-red scarf, brown wrist guards, dark-gray trousers, and worn boots must remain unchanged. The broom must remain the same dark aged wooden broom with silver-gray metallic fibers and a warm-gold front light. Do not add companions or other flying characters. Do not include pointed hats, school uniforms, magical schools, badges, school emblems, castles, recognizable film characters, superhero logos, or brand symbols. Do not generate text, subtitles, advertisements, UI elements, logos, or readable signs. Do not allow buildings to melt, drift, resize, or suddenly reorganize. Do not create duplicate figures in mirrors. Maintain realistic physical behavior for ice, rain, water, glass, fog, and clouds. Do not use hard cuts, sudden spinning, random shaking, abrupt zooms, body deformation, face replacement, explosions, large-scale destruction, or unmotivated effects. Keep the protagonist, broom, flying direction, city geography, and lighting transitions continuous and visually traceable.
- Ruling out references to known films forces genuinely original design instead of pastiche.
- Continuous camera movement with no hard cuts is stated twice, at style level and shot level, so it holds.
- Monumental scale is anchored by a human protagonist with believable proportions, which keeps the scale readable.
Dragon and Boy Timed Shot List
A compact four-shot escalation between a waking dragon and a terrified boy, each shot given its own duration and lighting shift.
Shot 1 (2.0s): An extreme close-up on @Dragon's closed eye as it suddenly snaps open, the golden iris contracting sharply. The camera holds tight and still, dust particles drifting past in the beam of light. Sharp, sudden shift in tension with a subtle lighting flicker. Shot 2 (2.5s): A quick, reactive medium shot as @Boy stumbles backward in fear, nearly tripping over rubble, his expression panicked. The camera shakes handheld, following his frantic retreat. Lighting shifts to a colder, harsher tone as shadows stretch across the hall. Shot 3 (3.0s): A powerful low-angle wide shot as @Dragon rises up, wings spreading and casting a massive shadow over the hall. It lets out a thunderous roar. The camera tilts up rapidly to capture its full towering height, dust and debris shaking loose from the ceiling. Dramatic high-contrast lighting with the beam from above now cutting harshly across the scene. Shot 4 (2.5s): A fast-paced action shot as @Dragon swipes its massive claws toward @Boy, who dives and rolls out of the way across the stone floor. The camera whip-pans to follow the motion, adding kinetic energy. Debris scatters, lighting flickers with dust kicked into the air. Shot 10 (2.5s): A dynamic tracking shot as @Boy scrambles behind a fallen pillar for cover, breathing heavily. @Dragon rears back, preparing to attack. The camera circles quickly around the pillar, low to the ground, building tension. Cold blue-white lighting dominates the frame. Shot 11 (3.0s): A dramatic wide shot as @Dragon unleashes a burst of icy breath across the hall, frost spreading rapidly over the stone floor and pillars. @Boy sprints and slides across the ground to dodge the blast, ice crystals forming in the air around him. The camera tracks low and fast alongside his movement, capturing the chaos. Shot 12 (2.0s): A final tense close-up as @Boy presses his back against a frozen pillar, chest heaving, staring up at @Dragon towering above him. The camera holds still, slowly pushing in. Cold light reflects off the newly formed ice, creating a striking, high-contrast final frame.
- Named entities with the @ prefix keep the dragon and boy consistent without a wall of description.
- Each shot carries its own duration, so the tension curve is authored rather than left to chance.
- Camera behaviour is specified per shot — held still, then handheld shake — which mirrors the emotional shift.
One Thousand Years from a Locked Camera
A thousand years pass over one patch of ground from a camera that never moves, with a mossy boulder present in every single frame.
A 30 second film from ONE completely locked, static camera position that never moves, never pans, never zooms, never cuts. The same view of the same patch of ground for one thousand years, time passing at enormous speed. In the foreground of every single frame sits a large mossy grey boulder. It never moves. It is present and recognisable in every frame of the film from first to last. [0:00-0:03] Ancient temperate forest. Huge old trees, deep green undergrowth, mist between the trunks, soft grey daylight. [0:03-0:06] Trees fall and are dragged away. A clearing opens. Stumps, churned mud, a first thin column of smoke. [0:06-0:09] A single timber and thatch hut rises beside the boulder. A small vegetable plot. Chickens. [0:09-0:12] A village grows around it. More huts, fences, a dirt track, wood smoke, sheep in the field beyond. [0:12-0:15] A stone wall is built, incorporating the boulder into its base. A church tower rises behind. Snow falls and melts. Seasons flicker past. [0:15-0:18] Fire. The village burns, timbers collapse, smoke blackens the sky. The wall and the boulder survive. [0:18-0:21] Rebuilding in brick. A cobbled road. A chimney, then many chimneys. Industrial smoke, grey air, rain. [0:21-0:24] The town becomes a city. Concrete rises. The old wall is demolished. The boulder sits in a small paved square, surrounded by buildings. [0:24-0:26] Glass towers. Traffic light streaking past at night. The boulder is fenced off, a small green plaque beside it. [0:26-0:28] Abandonment. Windows dark, glass cracked, weeds through the paving, ivy climbing the towers. Silence. [0:28-0:30] The towers have collapsed and gone. Young forest has grown over everything. Mist between the trunks. The frame is now identical to the opening frame, the same boulder in the same position under the same soft grey light. Camera: absolutely locked and static for all 30 seconds. No movement of any kind. No cuts, no dissolves, no transitions — one continuous transforming shot. Style: photoreal, cinematic, natural overcast light throughout, muted natural colour, seasons and weather flickering rapidly past. Audio: diegetic only, evolving with the era — forest birds, axes, village life, church bell, fire, industrial machinery, city traffic, then silence, then birds again. NO MUSIC, no score, no soundtrack, no instruments. No text, no captions, no titles, no watermarks, no camera movement, no cuts. created with @higgsfield
- A single unmoving anchor object gives the viewer a fixed reference so the passage of time reads clearly.
- The no-move rule is stated four ways — never pans, zooms, cuts, moves — leaving no interpretation room.
- Each era gets its own timecoded beat, so a thousand years has an authored rhythm rather than a blur.
Anamorphic Adventure One-Shot
A continuous adventure sequence specified by camera body, lens series and film stock rather than by look adjectives.
Authentic live-action cinematic footage captured as a continuous one-shot sequence on Arri Alexa 65 with Panavision Ultra Vista anamorphic lenses on real Kodak Vision3 35mm film. Ultra-photorealistic Hollywood adventure film aesthetic with natural film grain, cinematic depth of field, realistic handheld camera inertia, dynamic tracking shots, physically accurate motion blur, volumetric golden-hour sunlight, atmospheric jungle mist, practical lighting, realistic water simulation, authentic environmental interaction, and absolutely no CGI or game-engine appearance. A powerful Amazonian tribal warrior with weathered bronze skin, long braided black hair decorated with jungle feathers, athletic muscular build, worn leather tribal clothing, and intense recognizable eyes sprints through a dense rainforest while the camera performs an energetic low-angle tracking shot weaving between giant roots, rocks, vines, and tropical vegetation. He bursts out onto the edge of a colossal waterfall and leaps into the air as the camera dives beside him. During freefall his body organically transforms into a gigantic Amazon river crocodile with realistic skeletal restructuring, growing scales, extending jaws, muscular limbs, and a powerful tail before crashing into the river below. The camera follows underwater in one continuous movement as the crocodile powers through crystal-clear water, scattering schools of fish and passing submerged trees and ancient stone ruins. While swimming at high speed, the crocodile seamlessly transforms into a massive Amazon giant catfish with smooth biological morphing, retracting limbs, sleek skin, broad fins, powerful tail propulsion, and continuous identity preservation. The giant catfish accelerates through flooded jungle ruins before its body thickens and organically transforms into a colossal emerald anaconda with shimmering green scales, enormous muscular coils, and realistic serpentine movement as it glides through submerged temples and rises onto the rainforest floor. The colossal anaconda rapidly slithers through dense jungle while the camera performs fast ground-level tracking through mud, roots, and foliage. As it launches over a fallen tree, it seamlessly transforms into a powerful black jaguar with sleek black fur, muscular feline anatomy, realistic shoulder movement, explosive sprinting speed, and intense recognizable eyes. The jaguar races through the rainforest before reaching a towering cliff where it leaps into open air. During the jump, its body organically transforms into a majestic giant harpy eagle as black fur becomes feathers, forelegs expand into enormous wings, hind legs become massive talons, and the eagle catches an air current before soaring high above the endless Amazon canopy. The camera transitions into an FPV-style aerial pursuit as the harpy eagle flies between clouds toward an ancient mountain temple surrounded by waterfalls. The eagle folds its wings into a dramatic dive toward the summit. During the dive, feathers organically become skin, wings become human arms, talons become feet, and the original Amazonian warrior fully reforms with perfect facial identity, braided hair, and worn tribal clothing. He lands powerfully on the temple platform, rises slowly, and looks directly into the camera while the camera performs a slow cinematic push-in. Behind him, endless rainforest, waterfalls, drifting mist, and golden sunlight create an epic final hero shot before a slow fade to black. Maintain one continuous uninterrupted shot, seamless transitions, consistent character identity, realistic anatomy, believable body weight, physically accurate transformations, natural cloth simulation, hair physics, feather dynamics, water interaction, foliage collision, perfect environmental continuity, Hollywood blockbuster cinematography, ultra-photorealistic live action, no jump cuts, no visual glitches, no cartoon style, no artificial CGI, maximum cinematic realism.
- Naming a real camera, lens and stock combination gives the model a coherent optical package to imitate.
- Handheld inertia is requested as physics, so the movement has believable mass.
- Golden-hour volumetrics give the one-shot consistent lighting to travel through.
Palace Time-Loop Romance Drama
A vertical short-drama premise in which a murdered princess wakes the night before her death and confronts the prince she blamed.
A 30-second vertical 9:16 photorealistic fantasy palace romance drama about Princess Elara, who wakes up after being murdered and discovers she has returned to the night before her death. In a storm-lit royal palace, she confronts Prince Cassian, the man she believed betrayed her, only to uncover a deeper conspiracy and a magical fated bond between them. As the throne is threatened by a corrupt council, Elara and Cassian must overcome betrayal, unite as reluctant allies, and fight to reclaim the crown together. #StoryStudio #PippitAI #Seedance #PippitPartner
- The whole clip is driven by one reversal, which is enough narrative for a vertical short drama.
- Storm lighting supplies drama without any additional staging instructions.
- Writing it as a logline lets the model handle coverage, which suits this fast-turnaround format.
Hand-Pulling POV Walkthrough
A first-person walk led by a woman gripping the operator's wrist, with her hand visible in the lower right of frame the whole way.
image_1 is the first frame. The woman from image_1 — straight black hair, white short-sleeve collared shirt, navy pleated skirt, brown belt, braided bracelet — is holding the camera operator's hand and pulling him forward through the world. Camera is first-person POV, loose handheld, her hand visible in the lower right of frame gripping the operator's wrist, pulling. She walks ahead, glancing back over her shoulder occasionally. She walks, then runs, then sprints as the scale of the world gets bigger and more overwhelming. Every few seconds a vertical floor-to-ceiling insert appears ahead floating in open air — no border, no frame, no door, no arch, just a hard rectangular cut in space where one world ends and another begins — and she pulls him straight through it into the next world. Six locations total, one continuous uncut shot. Location 1 — 1970s apartment party interior from image_1: warm amber light, sequin curtain, strangers in background, she turns and pulls him out of the room forward. Location 2 — Petra, Jordan, midday: the narrow Siq canyon walls rising hundreds of meters on both sides, sunlight cutting down in a single strip, she runs pulling him through the corridor of ancient rock. Location 3 — Shibuya crossing, Tokyo, rush hour: hundreds of people crossing in every direction, she weaves pulling him through the crowd, neon signs and screens overhead in daylight. Location 4 — Sahara desert at golden hour: vast open dunes, no horizon line visible, wind moving the sand, she runs pulling him up a dune face, her skirt and hair flying. Location 5 — Venice, Italy, acqua alta flooding: St Mark's Square underwater, ankle-deep reflective water, pigeons displaced onto benches, she splashes forward pulling him across the flooded piazza. Location 6 — top of a mountain at dawn, clouds below: nothing ahead but open sky and light. She slows to a walk. Then stops. Still holding his hand. She turns and looks directly into the camera — directly at him — for the first time. Silence. Sound: party ambience fading, then canyon echo of running footsteps, then Tokyo crowd noise and distant traffic, then open desert wind, then Venice water splash and bells, then pure silence and wind at altitude. Her breathing gets heavier location by location. Style: photorealistic cinematic, 2.39:1 Cinemascope, warm film grain consistent across all six spaces, first-person handheld POV, one unbroken take from start to finish.
- Fixing the hand's position in frame gives the POV a constant physical connection to the guide.
- Declaring image_1 as the first frame anchors both the character and the starting composition.
- Her glancing back gives the camera a reason to keep following, which sustains a long walk.
Stylized 3D Beggar and Crow Short
A 30-second dialogue-free 3D animated short: a beggar shares food with a crow, the crow steals his banknote, and the chase ends with an unexpected gift.
Create a 30-second stylized 3D animated short with appealing rounded character design, expressive facial animation, tactile materials, warm cinematic lighting, playful physical comedy, and sincere emotion. No dialogue, subtitles, logos, or readable text. [0–5s — The Street] Frontal wide shot across a busy sidewalk: a weary, kind-eyed middle-aged beggar sits on the ground against an old stone wall, wearing the same patched coat and knitted cap throughout. A shallow donation plate rests in front of him. Pedestrians repeatedly cross between the camera and the beggar, briefly hiding him and emphasizing that he is overlooked. After one foreground passerby fills the frame, cut upward to a glossy black crow watching from a nearby tree branch, its head tilting with alert curiosity. [5–12s — Kindness] Return to the same frontal geography. A pedestrian takes the final bite from a half-eaten sandwich, pauses, and gently places the remaining half beside the beggar’s plate. Hold on the beggar’s grateful expression. The crow glides down and lands beside him. In a closer shared frame, the hungry beggar breaks off a piece of sandwich and offers it on his open palm. The crow cautiously takes it; their eyes meet, establishing trust. [12–16s — The Theft] A different passerby drops a paper banknote into the plate. Brief insert as it lands. The beggar’s shoulders lift, his tired face brightens, and he smiles with relief. Cut to the crow noticing this reaction. It snaps its head toward the plate, hops forward, grabs the same banknote in its beak, and launches away. The beggar freezes for one comic beat, then springs up and gives chase. [16–25s — The Chase] Accelerate through a clear, energetic multi-cut pursuit while preserving the crow’s route and the beggar’s direction of travel. The crow flies low between pedestrians; the beggar dodges around them, nearly collides with a fruit cart, regains balance, and keeps running. Lateral tracking through narrow streets between tall buildings; foreground bodies and street objects create fast parallax. The crow darts over the hood of a moving car at the last instant; the beggar skids past behind it as the driver brakes safely. Follow the banknote as the causal visual anchor, always secured in the crow’s beak. Alternate wide geography, close near-misses, and restrained handheld chase views. The crow finally turns into a quiet hidden courtyard and rises toward a wooden treehouse built inside a huge old tree. [25–30s — The Gift] The beggar follows up a rough wooden ladder and cautiously enters the small treehouse. Shift from frantic motion into stillness. Over his shoulder, reveal shelves and nests filled with many glittering found treasures: coins, paper money, rings, necklaces, brooches, watches, and polished trinkets. Warm golden shafts of light illuminate the collection. The beggar’s amazement slowly becomes an emotional smile as he realizes the crow deliberately led him here. The crow places the stolen banknote neatly on the treasure pile, turns toward him, and gives a mischievous, affectionate smile. End on a gentle two-shot of the unlikely friends beside the glowing treasure, with the crow nudging one small golden ring toward the beggar. Keep exactly one beggar, one crow, one sandwich, one donation plate, and the same stolen banknote throughout. Preserve clothing, character proportions, prop ownership, daylight direction, travel direction, and treehouse layout. Use expressive but believable body weight, cloth movement, wingbeats, landings, foot contact, traffic motion, and object interactions. Audio: lively city ambience, footsteps, cloth and paper rustle, soft crow calls, wingbeats, comic percussion during the theft, rapidly building orchestral rhythm through the chase, then warm strings and delicate piano for the final reveal.
- The story runs a complete arc — kindness, theft, chase, payoff — with each phase assigned its own timed block.
- The chase preserves the crow’s route and the beggar’s travel direction across cuts, which is exactly what keeps multi-cut pursuits spatially readable.
- The banknote is named as the causal visual anchor, giving every shot one object to track.
Action & Anime
Stress-test movement, impact, and spatial logic without losing continuity.
Rainy Subway Depot Martial Arts Duel
A modern hard-hitting duel in a disused elevated subway depot, cut invisibly so 30 seconds of fighting reads as one continuous take.
生成一段完整30秒、16:9横屏、24fps、写实电影级质感的现代近身格斗视频。使用我上传的两组人物参考图：第一名人物固定为“主角”，第二名人物固定为“敌人”。严格继承参考图中两人的面部、年龄、发型、体型、身高比例、服装、鞋子、配饰和整体气质。全程不得交换身份，不得变脸、改变服装颜色、改变体型或生成第三名参战者。 【核心风格】 参考《一个人的武林》所呈现的现代硬派武术电影气质：动作迅猛、贴身、凶狠，攻防转换极快，拳脚具有真实接触感和明确受力反馈，但不照搬电影中的人物、场景和具体镜头。以高质量ACT动作游戏的第三人称战斗镜头诠释两人对决，摄影机主要跟随主角，位于主角肩后、腰后或侧后方，使观众产生操控主角迎战强敌的沉浸感；关键格挡和重击时，可以短暂切入侧面中景或近景。 视频不要求真正一镜到底，可以在30秒内进行多次自然切镜，但整场战斗必须像一个连续长镜头般流畅。利用人物身体遮挡、立柱擦镜、快速摇镜、撞击震动和动作匹配完成隐形切镜。切镜后必须延续上一镜的动作惯性、人物位置、身体朝向、伤势和攻击方向，禁止瞬移、换位错误、人物突然恢复站姿或摄影机无理由越轴。 【场景】 深夜暴雨，一座已经停运的高架地铁检修站。站厅呈狭长矩形，地面是被雨水浸湿的深灰色防滑地砖，分布少量浅水洼，能够反射冷白顶灯和红色维修警示灯。左侧是一排金属检票闸机和关闭的卷帘门，右侧是半透明钢化玻璃护栏，护栏外能够看到高架轨道、雨幕、车灯和模糊城市建筑。站厅中段有三根粗大的混凝土立柱，柱脚带黄黑警示条，尽头是一段通往废弃站台的短楼梯。 冷白灯管是主要光源，其中两盏接触不良、偶尔闪烁；红色警示灯在墙面提供少量轮廓光。斜吹进来的雨水、潮湿薄雾、地面积水、立柱、护栏和闸机都要参与战斗。场景空间在所有镜头中保持一致，不得随切镜改变门、立柱、闸机和玻璃护栏的位置。 开场时主角位于站厅中段偏左，背后靠近检票闸机，面朝右前方；敌人位于右前方约三米处，背后是玻璃护栏。前半段战斗向站厅深处移动，中段绕过第二根立柱，后半段反向压回闸机区域。除非通过环绕镜头明确展示换位，否则敌人始终位于主角前方，保持清楚的行动轴线。 【动作原则】 动作由现代实战拳法、肘击、膝撞、低位踢击、近身控制、擒拿拆解和短距离摔法组成。主角冷静、精准、动作幅度小，善于格挡后立即反击；敌人力量更大、进攻性更强，擅长连续压迫和贴身撞击。敌人不是等待挨打的木桩，主角也不能全程无伤碾压。主角必须经历一次明显失势和一次危险化解，最后依靠判断和重心控制夺回主动。 每次进攻都必须呈现起点、运行路径、接触点和结果；格挡必须真正改变攻击方向；受击者的头部、肩膀、躯干、脚步和重心按照力量方向产生反馈。禁止隔空挥拳、拳脚穿透身体、没有接触却自行后退、无故旋转、连续空翻、悬浮和夸张飞行。动作速度快，但关键接触点必须清楚，不得用混乱残影掩盖动作。 【0—4秒：敌人抢攻】 第一帧已经处于战斗中，不进行对视、摆造型或绕圈试探。摄影机位于主角右后方约一米，接近肩部高度，采用轻微广角的第三人称ACT跟随视角。主角位于画面左侧偏中央，敌人从右前方快速逼近。前景是主角潮湿的肩膀和抬起防守的手臂，中景清楚呈现双方身体，背景是玻璃护栏、雨幕和城市灯光。 敌人右脚踩入水洼，水花向后飞散，同时右直拳攻击主角面部。主角小幅向左偏头，使拳锋擦过脸侧，左手从内侧拍开敌人手腕，右前臂立即架住敌人跟进的左摆拳。敌人不停顿，顺势用右肩和身体重量向前撞击。主角被迫后退半步，鞋底在湿地面短暂滑动，但立刻稳住。 敌人抬膝攻击主角腹部，主角双肘向内压住膝部，将冲击引向身体左侧，同时右脚切入敌人支撑腿外侧，为反击建立位置。摄影机跟随主角后退，敌人始终处于正前方。动作快速但不使用慢镜头。 【4—8秒：第一次反击】 敌人的膝部被压开，主角手臂从镜头前掠过形成遮挡，自然切换到两人右侧的平行移动机位。采用略低的中景，清楚展示脚步、髋部和拳肘路径。 主角左手控制敌人的右前臂，右拳从胸前短距离击中敌人右侧肋部。敌人的上半身因受力向左收缩，呼吸短暂中断，但立刻用左肘横击主角太阳穴。主角抬右臂挡住肘尖，前臂在碰撞中明显震动；随后转动肩膀，以左肘短击敌人胸口，再用右脚低位扫踢敌人左侧小腿。 敌人的左脚被扫得横移，但用右脚及时撑住，没有夸张腾空。他抓住主角上臂，将主角猛烈推向第一根混凝土立柱。摄影机随主角急速后退。主角后背接近立柱时用左掌撑住柱面卸力，沿柱边旋转躲避。敌人紧随而来的重拳擦过主角肩膀，砸中柱面，产生沉闷撞击、少量灰尘和疼痛反馈，但立柱不得碎裂。 【8—13秒：绕柱追击】 敌人击中立柱时，镜头产生一次短促撞击震动。主角快速绕到立柱另一侧，摄影机紧贴主角背后绕柱跟随。立柱短暂遮满画面，完成隐形切镜。遮挡结束后，主角位于立柱右侧，敌人从左侧追出，两人沿站厅纵深向楼梯方向移动。 敌人连续使用左右直拳压迫主角。主角边后撤边格挡：右掌向外拨开第一拳，左前臂贴住第二拳。敌人第三次攻击改为右腿中段踢击。主角来不及完全避开，只能收紧左臂保护肋部。踢击真实命中护臂，力量让主角向右踉跄两步，肩膀撞上玻璃护栏。玻璃发出沉闷震颤却没有破碎，护栏外的雨夜灯光因撞击产生短暂拖影。 敌人跨步逼近，左手压住主角肩膀，右肘攻击面部。主角在最后一刻低头，肘部从头顶掠过；主角左手抓住敌人上臂，右手控制手腕，尝试将其压向玻璃护栏。敌人凭借力量强行抽臂，以额头短促撞击主角眉骨。主角头部向后偏移，额角出现轻微擦伤，目光短暂失焦。 【13—17秒：主角失势】 头撞形成明确节奏重音。快速切入主角侧面近景，表现接触瞬间、飞散雨水和真实眩晕，随即拉回能够看清全身动作的中景，不使用长时间慢动作。 敌人抓住主角上身，将他从玻璃护栏方向拽回站厅中央，右腿绊住主角左腿，试图完成向前摔投。主角身体倾斜，在倒地前用右脚重新踩稳，并以左手勾住敌人后颈，双方进入短暂贴身角力。 摄影机从主角侧后方环绕约九十度，明确展示两人换位：敌人转到画面左侧，主角转到画面右侧，主角背后变为第二根立柱和闸机方向。敌人以力量将主角压在立柱边缘，进行一次肩撞和一次短膝击。主角用大腿与前臂挡住主要冲击，但仍因疼痛弯腰。敌人抬起右肘，准备从上方向下砸击主角后背。镜头靠近主角肩后，使抬起的肘部在画面中形成强烈威胁。 【17—22秒：危险拆解】 敌人的右肘快速下砸。主角不能凭空躲避，而是在肘击启动时向敌人身体内侧贴近，使肘尖从背后落空。主角左手托住敌人肘关节，右手控制其手腕，以肩膀作为支点向前旋转，破坏敌人的肩线。摄影机跟随主角完成半环绕，背景中的立柱、闸机和警示灯提供清楚的空间参照。 敌人为避免手臂被锁，顺势转身，以左拳反击。主角放开控制，低头闪过拳头，起身时用右肩撞击敌人胸口，将其推离立柱。主角立即以左直拳攻击敌人面部防守，迫使敌人抬高手臂；随后右拳从手臂下方击中腹部，再用左肘短击锁骨区域。三次攻击快速递进，但必须分别清楚，不能生成多条手臂。 敌人后退两步，脚后跟撞到检票闸机底座，随即用右腿横扫主角腰部。主角向前贴近，压缩踢击距离，以左臂承受大腿近端冲击，同时右手环住敌人腰侧，左脚踏到敌人支撑脚外侧。低机位镜头清楚交代主角如何控制敌人重心。 【22—26秒：环境摔投】 主角转动髋部并向斜前方发力，将失去支撑的敌人摔向闸机。敌人的肩背先撞在金属闸机侧面，闸机挡板被撞开并发出刺耳金属声，随后敌人落在湿地面，水花向外扩散。敌人的身体必须表现真实重量，不能轻飘飘飞行或在空中翻转多圈。 摄影机沿敌人落地方向快速俯冲，在触地时转为略高的斜俯视ACT视角。主角没有停下摆姿势，而是跨过被撞开的挡板继续追击。敌人翻身用右脚蹬向主角膝部，主角侧移避开。敌人借蹬腿动作翻滚起身，左手撑地，右脚踩稳，还未完全站直便挥出右摆拳。 主角从拳头内侧进入，左臂贴住敌人右臂，右掌推击敌人下颌。敌人向后仰头卸掉部分力量，同时左拳击中主角侧腹。主角明显收腹受击，却保持贴身距离，用右膝短促撞击敌人大腿前侧，进一步破坏其稳定性。两人呼吸加重，衣服逐渐湿污，但动作不能突然变得疲软。 【26—30秒：高潮反制】 摄影机回到主角左后方约一米的第三人称ACT跟随位置。主角位于画面中央偏左，敌人在正前方，背景保持被撞开的闸机、闪烁顶灯和红色警示灯。 敌人最后一次猛烈前冲，先用左拳虚晃主角面部，真正攻击是右肘横扫。主角没有被虚招骗出大幅动作，而是用右掌压下敌人左手，在右肘接近时向前踏入攻击内圈，左前臂架住敌人上臂，使肘尖从主角脑后掠过。主角抓住敌人后颈，右脚勾住其前脚踝，以肩膀向前下方施压。 敌人重心向后倒去，却抓住主角衣服试图将主角一同拖倒。主角立刻松开后颈，身体向左转出抓握，以右肘从极短距离击中敌人胸口偏肩位置，再用左掌推开敌人上胸。敌人向后撞在已经打开的闸机挡板上，挡板进一步弯曲。敌人半跪落地，一只手撑住湿地，另一只手仍保持防守，没有昏迷，也没有飞出画面。 主角受惯性影响向前半步，迅速重新稳住重心，双手保持防守，没有背对敌人、庆祝或摆胜利造型。摄影机缓慢移动到主角右侧，以主角肩膀作为前景，将焦点落在半跪喘息、暂时失去进攻能力的敌人身上。红色警示灯闪烁一次，远处传来雷声。最后一帧保持双方继续互相锁定的危险状态，让主角暂时占据优势，但为下一段战斗留下自然衔接。 【摄影、画面与声音】 保持电影级实拍质感与ACT游戏镜头的融合。主要采用肩后跟随、侧后跟随和腰部高度移动机位；关键命中使用短暂侧面中景或近景。摄影机移动快速但具有真实重量，不得漂浮、瞬移、疯狂旋转或持续无规则抖动。撞击时只使用极短、低幅度震动，震动方向与力量方向一致。 动作中允许适量运动模糊，但人物面部、手脚和接触点在关键时刻保持清晰。禁止鱼眼、长时间慢动作、子弹时间、冻结画面、速度线、游戏血条、准星、按钮提示和文字UI。ACT感来自主角中心构图、第三人称跟随、空间推进和及时的动作反馈。 超写实皮肤、肌肉牵拉、衣料褶皱、湿润头发、汗水和雨水反射；真实金属、混凝土、玻璃与湿地砖材质。冷蓝灰色为主色，冷白顶灯作为主光，红色警示灯作为局部轮廓光。高对比但保留暗部细节，高光不过曝，地面反射自然。禁止蜡像皮肤、塑料CG质感、噪点、脏污颗粒、锐化白边和压缩色块。 生成严格同步的现场声音：雨击顶棚、远处雷声、脚踩积水、湿地摩擦、衣料摆动、急促呼吸、拳掌击中皮肉、前臂格挡、肘膝碰撞、身体撞柱、玻璃震颤和闸机金属回响。无需对白。音乐仅保留极其克制的低频脉冲，不能盖过格斗音效。 【负面约束】 禁止身份互换、面孔漂移、服装变化、身体比例突变、多余人物、复制人物、多手多脚、关节反折、身体穿透和人物粘连；禁止隔空受击、动作没有惯性、敌人静止等待、无故滑行、瞬移、悬浮、武侠轻功、气功、能量特效、夸张冲击波和墙体爆炸；禁止主角全程无伤碾压，禁止敌人只会挨打；禁止无意义空镜、英雄登场、长时间对视、重复招式和结尾突然黑屏。 最终效果必须呈现清晰的动作结构：敌人强势抢攻、主角短暂反击、绕柱追击、主角失势、危险拆解、重新夺回主动、利用闸机完成摔投和最终反制。30秒全程高强度、无废秒，刺激而不混乱，凶狠但遵守人体力学，摄影机始终以主角为核心。
- Invisible cut techniques are listed explicitly — body occlusion, pillar wipes, whip pans, impact shake — so the model has real tools.
- Post-cut continuity rules cover position, facing, injuries and attack direction, which is where fight sequences usually break.
- A third-person over-the-shoulder camera borrowed from action games gives the coverage a consistent logic.
30s reads as one fightInvisible cutsGrounded contact
Bladesmith Competition Test Segment
A reality-TV blade-testing segment: a master chops three ceramic gnomes in slow-motion freezes, then delivers the verdict to the young bladesmith.
Reality TV bladesmith competition testing segment, multi-camera documentary production, bright industrial workshop lighting, sharp HD broadcast look, practical forge practicals, natural handheld shake on action cams, clean documentary texture, no cinematic film look. 0-4s: [Medium Two-Shot] Martial arts master of clear Asian ancestry in black tactical shirt stands facing the young female bladesmith in her early 20s (work apron, focused). He holds her forged machete, turns the blade once under the lights. Looks her in the eye: “Are you ready?” She answers firmly “Yes.” Quick cut to her determined face, then to three classic ceramic garden gnomes lined up on sturdy stands behind them. 4-7s: [Low-Angle Tracking + Rapid Cuts] Master steps in, raises the machete. Hard cut to side angle as he delivers a powerful overhead chop into the first gnome. Impact explodes in slow motion: ceramic shatters into sharp fragments, paint chips and dust fly outward. Time locks at peak penetration. Camera orbits the frozen blade buried in the broken gnome for one second. Quick insert ECU of the edge biting through the ceramic body. 7-11s: [Dynamic Side Tracking] Action resumes. Master yanks the machete free, immediately follows with a heavy diagonal slash across the second gnome. Slow-motion again: the figure tears apart sideways, large colored pieces and shards scatter. Freeze at maximum destruction. Two rapid cuts: one over-shoulder from behind the master, one low angle under the flying fragments. Orbit holds for half a second on the locked impact. 11-15s: [Handheld Close Action] Third strike — short, vicious downward chop into the third gnome. Slow-mo impact, the ceramic erupts into dozens of pieces, hat and beard flying. Full freeze. Camera pushes in and circles the frozen chaos for one beat. Quick insert of the master’s focused face mid-swing, then back to the locked blade. 15-19s: [Series of Fast Cuts] Time resumes. Master pulls the machete out, turns it under the light. Tight ECU tracks along the edge: a few small nicks and rolled spots visible. Cut to his fingers testing the edge. Cut to the ruined garden gnomes still shedding fragments. Cut to the young woman’s tense expression as she watches. 19-24s: [Medium Close-Up] Master lowers the blade, looks straight at her. Calm, professional delivery: “There are a couple of nicks on the edge… but your weapon, ma’am… it kills.” Hard cut to her face — a small, controlled smile of pride breaks through. 24-28s: [Final ECU Montage] Extreme close-up of the nicked but still lethal edge catching the light. Cut to the shattered remains of the garden gnomes. Final frame holds on the young bladesmith’s quiet satisfaction as the master nods once. Realistic TV broadcast quality, detailed ceramic shatter physics, sharp edge detail, natural motion blur only on moving elements, stable characters, coherent impact timing, no artifacts, high rewatch value.
- Every strike names the contact, the material response and the aftermath — shattered ceramic, flying paint chips, nicks on the edge — so the physics reads as real.
- The broadcast container (multi-camera reality TV, action cams, no cinematic look) sets lighting, texture and editing grammar in one line.
- Two short scripted lines bookend the action, giving the segment a verdict structure instead of a loose montage.
Top-3 X engagementFreeze-frame impact physicsReality-TV broadcast look
Aerial Storm Action Spectacle
A dialogue-free 30-second aerial spectacle stacked with speed ramps, whip pans and match cuts through volumetric storm clouds.
30-second cinematic aerial action spectacle, breathtaking high-budget feature film, ultra-dynamic editing, fluid aerial choreography, premium cinematic visuals, seamless kinetic camera movement, aggressive speed ramps, rapid match cuts, whip pans, rotating camera moves, dramatic perspective shifts, cinematic lens distortion, volumetric storm clouds, ocean spray, glowing tracer lights, smoke trails, sparks, flying debris, colossal scale, emotionally epic, no dialogue. 0–5s Dark storm clouds gather above a vast open ocean. A colossal armored battleship cuts through enormous waves. Far above, a lone high-performance fighter aircraft emerges from the clouds. Extreme close-ups. Pilot visor. Hands on the controls. Jet intake vibrating. Radar display glowing. The camera alternates between immense aerial vistas and intimate cockpit shots. Complete silence. 5–10s The fighter rolls onto its wing and dives toward the ocean. The camera races only meters from the aircraft before instantly switching to first-person cockpit views, impossible wing-mounted perspectives, sweeping aerial fly-bys and dramatic low-angle shots skimming above the waves. The ship rapidly grows larger. The engines reach full power. 10–15s A breathtaking aerial montage. The fighter slices between towering smoke columns and dense clouds. Bright streams of tracer light streak across the sky. The aircraft performs impossible barrel rolls, high-G turns and vertical climbs while the camera continuously rotates around the fuselage. Speed ramps amplify every maneuver. 15–20s The fighter skims just above the ocean surface. Towering walls of spray rise behind it. It climbs sharply over the battleship's deck in one uninterrupted shot. The camera dives beneath the aircraft, then whips upward through drifting smoke, sparks and sunlight breaking through the storm. Everything feels impossibly fast. 20–25s The sequence reaches maximum intensity. The aircraft circles the massive vessel at incredible speed. Towering water plumes erupt around the ship. Clouds swirl overhead. The camera jumps between ultra-wide aerial compositions, intimate cockpit close-ups, spinning chase shots, dramatic slow-motion fly-bys and impossible orbiting movements around both aircraft and ship. Every cut increases the spectacle. 25–30s Everything suddenly slows. The fighter climbs vertically through the storm clouds into brilliant sunlight. Far below, the gigantic battleship disappears beneath drifting mist and shimmering ocean reflections. The camera pulls rapidly upward into an immense aerial shot revealing endless sky and sea stretching to the horizon. Hard cut to black. Sound design: soaring cinematic orchestra, thunderous percussion, deep brass, roaring jet engines, rushing wind, ocean waves crashing against steel, atmospheric echoes, powerful fly-by whooshes, subtle sonic booms, cinematic bass swells, brief silence before the final climb, overwhelming orchestral finale.
- The editing vocabulary is declared up front as a list, so every beat inherits the same kinetic grammar.
- Removing dialogue lets the model spend the entire budget on movement and scale.
- Volumetric clouds, spray and tracer light give the camera moves something to cut through, which sells the speed.
Speed ramps & whip pansMatch cuts through stormDialogue-free 30s
Sakuga Anime Action Sequence
A high-budget anime fight built on fluid sakuga animation, aggressive speed ramps and rapid match cuts.
30-second cinematic anime action sequence, breathtaking high-budget anime film, ultra-dynamic editing, fluid sakuga animation, spectacular fight choreography, seamless kinetic camera movement, aggressive speed ramps, rapid match cuts, whip pans, rotating camera moves, dramatic perspective shifts, cinematic lens distortion, volumetric lighting, dust, sparks, debris, explosive impacts, emotionally intense, premium animation quality, no dialogue. 0–5s A ruined futuristic city stands silent beneath storm clouds. Two lone warriors face each other hundreds of meters apart. The camera rapidly alternates between extreme wide shots, close-ups of determined eyes, hands tightening around weapons, feet scraping broken concrete, fluttering coats and drifting dust. A heartbeat. Absolute silence. 5–10s Both fighters explode forward simultaneously. The camera races alongside them before instantly switching to overhead drone views, impossible low angles beneath their feet, first-person perspectives, and ultra-fast lateral tracking shots. Shockwaves ripple across the ground as they collide. The first impact sends debris flying in every direction. 10–15s An overwhelming combat montage. Lightning-fast sword strikes. Acrobatic flips. Mid-air clashes. Wall running. Buildings collapse around them. The camera never stays still: continuous orbit shots, rapid whip pans, rotating 360-degree movements, crash zooms, Dutch angles, seamless transitions through clouds of dust and sparks. Constant speed ramps amplify every decisive strike. 15–20s The battle escalates. Energy erupts with every collision. One fighter launches the other through multiple rooftops. The camera follows in a single uninterrupted shot before cutting to an extreme close-up as both instantly reappear, colliding again in mid-air. Fragments of glass, steel and concrete freeze momentarily before exploding outward. 20–25s The choreography becomes almost impossible to follow. Dozens of rapid exchanges. The camera jumps between ultra-wide cinematic compositions, intimate facial close-ups, spinning aerial shots, slow-motion impacts, handheld ground-level tracking, and impossible anime-style perspective shifts. Every cut increases the intensity. The music reaches its peak. 25–30s Everything suddenly slows. The two warriors cross paths one final time. Silence. A single decisive strike. The camera follows the blade in extreme slow motion before rapidly pulling back into an enormous aerial shot revealing the devastated city beneath dark skies. Dust slowly settles. Hard cut to black. Sound design: colossal cinematic orchestra blended with modern hybrid percussion, taiko drums, distorted synth pulses, thunderous impacts, rushing wind, metallic blade clashes, explosive shockwaves, collapsing buildings, debris showers, aggressive cinematic whooshes, deep bass hits, brief silence before the final strike, overwhelming orchestral finale with massive surround sound.
- Sakuga names a specific animation tradition, which gets a much sharper result than fluid animation would.
- Editing techniques are listed as style, so every shot inherits the same kinetic approach.
- Dust, sparks and debris give the impacts physical consequences to animate.
Fluid sakuga animationAggressive speed rampsRapid match cuts
Youth Racing Anime Film
A 30-second cinematic 2D-anime racing short with a clear emotional arc, using only high-speed tracking and slow-motion orbits.
A 30-second cinematic youth-racing story short, 2D animation style. The protagonist is a teenage rider, racing a motorcycle in a high-level competition. The overall style is hot-blooded, youthful, emotionally intense, and strongly cinematic, with a complete dramatic structure and a clear emotional arc. The whole film uses only two camera moves: high-speed tracking and slow-motion orbit. Dialogue is minimal, appearing naturally like fragments of memory, the tone sincere, gentle, and restrained, no slogans, no over-sentimentality. No sense of disaster, no negative expression, no exaggerated sci-fi. The focus is on the love, support, fight-back, and growth within youthful racing. 0s to 5s: A dusk racetrack, a high-speed intense racing opening. The camera hugs the ground in high-speed tracking of the teen's motorcycle, tires grazing the track's edge line, the bike roaring, the wind sharp, the atmosphere tense and fervent. The teen is fully focused, the setting sun drawing sharp highlights across the bike's metal shell. 5s to 9s: After entering a key corner, the teen is suddenly overtaken by a rival. The high-speed tracking keeps pushing forward, the image conveying the pressure of a dropping rank and a disrupted rhythm. A close-up inside the helmet shows a brief daze, tightening breath, slight wavering. The teen says quietly: "Can I still catch up..." 9s to 14s: The teen falls behind, breathing heavier, his emotions sinking into a low point. The race doesn't stop, the bike still racing forward at high speed. The image begins to flash back to warm memory fragments amid the high-speed riding: as a child learning to ride, someone steadying him from behind; his father adjusting his helmet, the motion careful and quiet; before the finish line, a gentle smile watching him; on a dusk slope, the silhouettes of figures walking side by side. These memories are all presented with golden backlight, soft slow motion, and a fragmented feel. 14s to 18s: The music gradually turns from oppressive to uplifting. Restrained, gentle voices come from the memories: "Don't be afraid - I'm always here." "Stay steady. And look forward." The teen's gaze refocuses, his breathing slowly steadying, his emotions shifting from wavering to resolute. 18s to 23s: The teen regains his belief, accelerating with all his strength, fighting back with precise cornering lines. The high-speed tracking conveys the power and control of the bike leaning into the corner, exiting the corner, and closing in on the lead car. The teen says quietly but firmly: "I won't stop here." 23s to 27s: Ahead appears a rising stretch of track, the teen sprinting at full speed into the setting sun. The image keeps only the sound of breathing, the engine, and the continuously rising music, with no more extra dialogue. The bike launches into the air on its momentum, entering a stunning slow motion. From deep in his memory comes one last gentle voice with a smile: "Go on." 27s to 30s: The camera makes a slow-motion orbiting close-up around the airborne bike, pushing the hot-blooded, gentle, free, soaring-upward emotion to its climax. Flowers bloom behind in a special effect, then "seedance" appears, see [reference image 1].
- Restricting to two camera moves gives the emotional story a consistent, cinematic visual grammar.
- Memory-fragment flashbacks deepen the arc without breaking the race momentum.
- A clear setup-fall-fightback-soar structure delivers a satisfying emotional payoff.
Samurai Trailer With a 30-Second Timeline
A Japanese shot plan that builds a mounted samurai reveal through armor macros, controlled transitions, acceleration, and a final hero shot.
方向性 甲冑と馬のディテールを高速で見せながら、後半で騎馬武者として完成させる。 前半は緊張感、後半は疾走感。 全体は映画予告編のような迫力のあるテンポで展開する。 0.0〜2.0秒｜強い導入 映像 黒画面から、金色の兜の前立てだけが強い光を受けて浮かび上がる。 カメラ 超クローズアップ。 兜の中央から始まり、0.8秒ほどで急速にプッシュイン。 演出 金属音に合わせて一瞬だけ白くフラッシュ。 すぐに暗転せず、そのまま次のカットへハードカット。 2.0〜4.0秒｜面頬と眼差し 映像 黒い面頬、目元、兜の下の影を見せる。 カメラ 左斜め下から右上へ高速スライド。 途中でごく短いスピードランプ。 ポイント 顔全体を長く見せず、目元と面頬の質感で強さを出す。 4.0〜6.0秒｜刀の準備 映像 右手が刀の柄を強く握る。 鞘と金具がわずかに揺れる。 カメラ 腰元のマクロショット。 刀の柄に沿って横方向へ高速トラッキング。 演出 金属が擦れる短い効果音。 完全な抜刀はまだ見せない。 6.0〜8.0秒｜馬の登場 映像 馬の前脚が地面を踏み鳴らす。 砂や土が飛ぶ。 カメラ 地面すれすれのローアングル。 蹄を追いながら前方へ移動。 演出 蹄の着地に合わせて画面を小さく揺らす。 8.0〜10.0秒｜馬の顔と手綱 映像 馬が鼻息を吐き、首を振る。 手綱が張る。 カメラ 馬の顔の斜め前から、首筋へ高速パン。 最後に鞍で止める。 ポイント 馬全体ではなく、顔・首・鞍を連続的につないで見せる。 10.0〜12.5秒｜侍と馬が同じ画面に入る 映像 侍が馬の横に立ち、左手で手綱を取る。 カメラ 足元から開始し、兜まで一気にティルトアップ。 最後に少し引いて、侍と馬の全体像を見せる。 演出 風で甲冑の紐、馬のたてがみ、布が揺れる。 12.5〜15.0秒｜騎乗への移行 映像 侍が馬へ乗ろうと踏み込む。 カメラ 侍の背後から高速で接近。 身体が画面を大きく遮った瞬間に、騎乗後の画へ切り替える。 重要 実際の騎乗動作を全部見せない。 身体、旗、砂埃などを画面いっぱいに入れて、自然に状態を切り替える。 15.0〜18.0秒｜騎馬武者の完成 映像 侍が馬上で手綱を握る。 馬がゆっくり歩き始める。 カメラ 馬の左側面から並走するミディアムワイド。 少しローアングルで、騎馬武者を大きく見せる。 演出 ここだけ一瞬テンポを落とし、完成した姿を見せる。 18.0〜20.5秒｜正面突進 映像 馬が歩行から速歩へ移行し、正面へ向かってくる。 カメラ 正面ローアングル。 カメラは後退しながら馬を追う。 ポイント 馬と侍を画面中央に固定し、背景だけが高速で流れるように見せる。 20.5〜23.0秒｜横方向の疾走 映像 騎馬武者が画面左から右へ駆け抜ける。 カメラ 高速サイドトラッキング。 一瞬だけ馬の脚、甲冑、刀をクローズアップで差し込む。 編集感 0.5〜0.8秒の短いカットを3つ入れる。 馬の脚、侍の手、甲冑の揺れ。 23.0〜25.5秒｜抜刀 映像 侍が右手で刀を抜く。 刀身が光を反射する。 カメラ 右斜め前から半円状に回り込む。 抜刀と同時に速度を上げる。 演出 刀身が画面を横切った瞬間にワイプのように次のカットへ移行。 25.5〜28.0秒｜ヒーローショット 映像 丘の上で馬が立ち止まり、侍が刀を構える。 背後に朝日、霧、旗。 カメラ 背後の低い位置からゆっくり上昇。 騎馬武者をシルエット気味に見せる。 ポイント ここは高速ではなく、2.5秒かけて余韻を作る。 28.0〜30.0秒｜締め 映像 侍が刀を下ろし、馬が一歩前へ出る。 砂埃が画面を覆う。 カメラ 正面のミディアムロング。 最後の一歩に合わせて急速にプッシュイン。
- Every beat separates visual action, camera direction, and sound or transition intent.
- The pacing deliberately slows for the completed mounted-samurai reveal before accelerating again.
- Foreground occlusion, blade wipes, and dust provide motivated transitions instead of arbitrary cuts.
Hand-Drawn Emotional Chain Reaction
A fully hand-drawn abstract piece where an emotional core erupts and every element of the frame — figure, background, texture — keeps reacting to it.
Core Style: Fast, vivid, unstable. Fully hand-drawn with rich organic textures. Every transition is fluid and natural—never rigid or mechanically cut. The entire frame, including the background, remains in constant motion, driven simultaneously by emotion, gravity, and heat. Every frame should feel alive, unpredictable, and physically reactive. [0–7.5s: Origin and Chain Reaction] [0–1.5s] A central abstract figure erupts into violent motion. Its emotional color core radiates outward as irregular pulsating waves while its silhouette tears apart in multiple directions. The background bends around the figure like compressed soft paper. Fine hand-drawn textures crawl rapidly across the entire frame, moving significantly faster than the figure itself, creating intense tension between body, skin, and surface. [1.5–3s] The separated contours accelerate into nervous linear forms. The figure's colorful core stretches into sharp ribbons and liquid stains. Some ribbons snap backward while others whip violently forward, leaving trembling trails behind. Empty spaces between movements ignite into new forms that emerge to fill emotional voids. [3–4.5s] Every shape surges diagonally across the composition. One massive form folds like fabric, revealing layered textures of grain, chalk, wet ink, scratched paint, and rough pigment beneath its surface. The background folds together with it, twisting into entirely new color fields. Smaller forms are dragged into constantly evolving speed lines. [4.5–6s] The image fractures into four emotional forces: calm, violence, vulnerability, and ecstasy. Each absorbs color from the others. Shadows appear before their objects, behaving like prophecies. The original forms chase these shadows, but the shadows mutate faster—becoming brighter, thicker, and more dominant until they surpass the objects themselves. [6–7.5s] A rapid chain reaction begins. Colliding forms generate visual motifs derived from the reference imagery: fragments, symbols, silhouettes, stains, and expressive linework. These newly born motifs accelerate in different directions. Frozen traces solidify into new entities before melting again and splitting into tiny emotional echoes. --- [7.5–15s: Compression and Extreme Transformation] [7.5–9s] The entire frame collapses toward an invisible point beneath the center. Every visual layer compresses inward at a different speed. Maximum compression lasts for only one frame before exploding upward and outward with vertical smears, shaking outlines, and exaggerated overshoot motion. Every element vibrates before settling into a completely new position. [9–10.5s] Textures migrate between forms. Dry rough textures sharpen previously fluid shapes into angular structures. Liquid textures soften rigid forms until they sag and drip. Luminous colorful textures dissolve into the background, causing the environment itself to pulse rhythmically. Every object changes behavior according to the texture it inherits. [10.5–12s] A massive rotational force sweeps across the frame. Every form flips, inverts, or turns inside out, exposing hidden reverse sides possessing qualities of hands, hooks, flames, or waves. Every collision triggers escalating chain reactions, transforming the entire visual world into an entirely new emotional reality. [12–13.5s] All boundaries dissolve. Forms merge, repel, and merge again, generating hybrid entities that inherit the colors and movement of their predecessors while becoming completely different beings. The background pushes forward into the foreground, becoming part of the forms themselves while releasing new shapes from within. [13.5–15s] Every previous process returns simultaneously at maximum intensity: contour separation, color bleeding, texture migration, and shadow-leading motion. Every frame is densely packed with intentional visual impact, fully absorbing and reinterpreting every reference element introduced earlier. --- [15–22.5s: Fragmentation and Neurotic Storm] [15–16.5s] The storm collides with an invisible barrier. The center explodes into countless shards of water-covered broken glass. Within each fragment, glowing spiral irises rotate violently, generating centrifugal force that stretches and tears at the shard edges. Neon magenta and electric blue leak through every crack. [16.5–18s] The fragments fuse into overlapping collaged human faces. The faces are composed of purple stains, scratched paint, and rough pigment. Their expressions oscillate continuously between terror and ecstasy. Jagged lightning-like lines pierce through them like exposed nerve fibers, violently stitching the faces together. [18–19.5s] Color saturation reaches its peak. Electric blue lines solidify into physical cables stretching throughout space, twitching uncontrollably while releasing neon magenta sparks. The compressed paper background burns away, transforming into a charred, granular carbon-black surface. [19.5–21s] Gravity reverses. Liquid elements such as water droplets and wet ink surge upward while broken glass continues falling downward, producing intense visual tearing. Vertical smears appear along the edges of the frame as though an unseen force is physically wiping the entire animation off the canvas. [21–22.5s] Every form is pulled into countless miniature spiral-iris black holes. The irises rapidly expand until they dominate the entire screen, spinning at an increasingly suffocating speed. The rough tactile quality of chalk and dry brush textures contrasts violently against the brilliant electrical center, creating overwhelming sensory overload. --- [22.5–30s: Aftershock and Eternal Echo] [22.5–24s] The giant iris evolves into pulsating biological tissue. The image breathes with a neurotic rhythm. Hidden symbols and textures appear and disappear beneath muscular contractions. Paint seepage creates convincing depth, as though layered across multiple transparent sheets of film. [24–25.5s] The animation enters an intense high-frequency vibration. Every object freezes in place while its edges oscillate violently like strings stretched to their breaking point. Violet shadows crawl across every surface, attempting to consume the remaining light. [25.5–27s] Rainbow-colored glass fragments and water droplets sweep across the frame like rain, refracting and distorting everything behind them through lens-like optical effects. Colors become heavy fluid masses that sink downward, leaving behind anxious, restless linear marks. [27–28.5s] The entire composition collapses into a single glowing horizontal jagged line. The background becomes a dark neon field filled with coarse grain. The line contains all accumulated energy, twisting violently while alternating flashes of electric blue and neon magenta pulse across it. [28.5–30s] The glowing line disintegrates into hand-drawn dust particles that drift rhythmically across the screen before gradually reassembling into one enormous blurred luminous silhouette. The final frame ends with tiny blocks of color continuing to vibrate subtly, leaving behind an everlasting emotional aftershock.
- The style block is declared once up front, so the long timeline never has to restate the look.
- Requiring the background to move with the figure prevents the flat, pasted-on feel of most abstract animation prompts.
- Emotion, gravity and heat are named as the three motion drivers, giving the model a physical logic to animate against.
IMAX Golden-Hour Field Operative
A golden-hour operative sequence built on strict camera rules — low angles and crash zooms only, never an orbit — with the second character present only as filtered radio.
Prompt 👇 Jan: tall slim, round red glasses, earpiece right ear, gloves, harness. Tone: IMAX anamorphic 2x, golden hour. Hard low sun on wet concrete, deep blue shadows, backlight, horizontal blue flares, saturated epic grade. Never grey or flat. CAMERA: low angle nearly every beat. Crash zooms, straight tracking, tilts. NEVER orbit or arc. Smooth motion, natural blur, 24fps, no stop motion. Jan never looks into the lens. AUDIO: Renteria only by radio, thin, tinny, filtered, click each side. Jan answers out loud. SFX only: wind, rotor, rope, fabric. NO MUSIC, no subtitles. 0-6s Ground-level low angle, sun flare on puddles. Crash zoom to Jan's hands snapping the case shut, tilt up to earpiece and face, front to camera. Renteria, urgent: "Treinta segundos, Jan. Cincuenta referencias. Una sola toma. Tienes que mandarlo ya." 6-9s Low angle into the sun, camera tracks back ahead of Jan. He lifts the case: "Enterado. Voy por el." and runs. 9-12s Water-level low angle. Jan sprints over the camera, jumps a duct, gold spray on the lens. Renteria: "Cuando te subas, abres tu Capcot y lo generas ya." 12-15s Low angle on Duarte, rim lit. Crash zoom: "Pense que llegabas mas tarde." 15-18s Low angle, helicopter drops into a low hover, rotor wash blasting gold spray. Jan steps up through the door. 18-21s Cabin, over the shoulder behind Jan. He opens the case revealing the laptop, screen square to camera. Push in as he presses Generate. 21-25s Jan clips a rappel line to his harness, grips it with both gloved hands, kicks off the skid and swings out over the facade. Camera whips down with him into a fast controlled descent, boots striking the glass, sunlight tearing past. 25-30s Epic finale. Mid descent Jan yanks a second rope hard. The giant banner bursts open beside him and unrolls floor by floor, snapping taut. He lands on his feet in the plaza. Crash zoom out to a vast skyline wide, the full banner reading ESTO ES SEEDANCE 2.5 above him, helicopter rising into the sunburst.
- The camera section is written as permissions and bans, so the model cannot fall back on its default orbiting move.
- Putting one character on radio only means the model never has to stage or match a second face.
- Grade instructions are stated as a hard rule (never grey or flat), which holds the look across every beat.
Cartoon Bulldog vs Live-Action Boxer
A ten-shot boxing match that keeps a hand-drawn 1960s cartoon bulldog and a photoreal human boxer in the same ring without either drifting toward the other.
Use Image 1 for the large muscular cartoon bulldog boxer, Image 2 for the live-action Caucasian American boxer, and Image 3 for the vintage arena, ring, crowd, and lighting. Create an intense 24-second boxing sequence in 10 shots. The bulldog remains a hand-drawn 2D character inspired by 1969 American TV cartoons, keeping the same face, proportions, red gloves, and striped shorts. Never make him realistic. The human boxer remains fully photorealistic. Style: heated live sports documentary broadcast. Handheld ringside cameras, reactive pans, imperfect reframing, small zoom corrections, natural shake, motion blur, focus breathing, faded 35mm colors, soft lens bloom, subtle gate weave, and naturally changing film grain. No frozen grain or fixed texture. Strong white spotlights illuminate the ring. The crowd is darker but visible and constantly reacting. Crowd cheering continues from the first frame to the last: shouting, applause, whistles, and stomping. Reactions grow louder after major punches. An excited male English commentator speaks continuously. No music. Each numbered shot is one continuous camera take. The camera may pan, track, dolly, or reframe, but must not jump to a new position inside the same shot. Comic effects must resemble authentic 1969 American comics: imperfect hand-drawn lines, thick black outlines, red, yellow, white, and black colors, halftone dots, faded ink, and slight print misregistration. Use effects sparingly: SPEED LINES on fast punches. One-frame SMEAR FRAME on the strongest punches. Small IMPACT BURSTS on selected hits. IMPACT FLASH and SHOCKWAVE RING only on the decisive counter and final uppercut. WOBBLE LINES and yellow rotating stars only when the human is badly dazed. Use only these comic sound effects on major clean hits: THWACK! POW! SMACK! WHAM! CRACK! SHOT 1 — 0.0–2.0 High-angle view of the packed arena. The ring is under strong spotlights. Both fighters wait in opposite corners. The bell rings, the crowd erupts, and both walk toward the center as the camera pushes closer. SHOT 2 — 2.0–4.0 Slightly elevated wide shot from outside the ring with ropes in the foreground. The referee steps back. Both fighters raise their guards, circle, and test distance. The handheld camera tracks right. SHOT 3 — 4.0–6.2 Low canvas-level angle. The bulldog throws a jab with brief SPEED LINES. The human narrowly avoids it and counters with a jab that the bulldog blocks. Quick natural pan. No comic text. SHOT 4 — 6.2–8.8 Slightly high-angle shot through the ropes. The human attacks with a combination. A left jab lands with a small IMPACT BURST and THWACK! A right straight follows with POW!, a brief IMPACT FLASH, and a small burst. A left hook lands with only a subtle impact mark. The camera tracks as the bulldog retreats. SHOT 5 — 8.8–11.2 Close handheld shot from the opposite side. The human keeps pressing with short punches. The bulldog blocks several and absorbs one body shot. The camera urgently reframes. The bulldog answers with a short face hook using a small red IMPACT BURST and SMACK! SHOT 6 — 11.2–14.0 Over-the-shoulder from behind the human. The human throws a powerful right straight. The bulldog slips underneath. The camera pans with the missed glove. Without cutting, the bulldog plants his feet, rotates, and launches a right counterpunch with SPEED LINES and a one-frame SMEAR FRAME. SHOT 7 — 14.0–16.8 Tight ringside impact shot. The bulldog’s right straight lands on the human’s cheek in very brief slow motion. His cheek compresses and sweat flies. At contact, show a large IMPACT BURST, white IMPACT FLASH, radial lines, short SHOCKWAVE RING, and WHAM! The effects vanish immediately. Return to normal speed as the human staggers backward. The crowd explodes. SHOT 8 — 16.8–19.2 Slightly elevated ringside shot. The human is badly dazed but standing. WOBBLE LINES and three yellow stars briefly appear. The bulldog lands one body punch without text, then a short face hook with SPEED LINES, a small burst, and SMACK! SHOT 9 — 19.2–21.5 Low diagonal ringside angle. The bulldog throws a compact uppercut with a one-frame SMEAR FRAME. It lands under the chin with IMPACT FLASH, red-yellow IMPACT BURST, short SHOCKWAVE RING, and CRACK! The human falls into the ropes, drops to one knee, and collapses safely. The referee stops the fight. The bulldog steps back. Yellow stars fade. SHOT 10 — 21.5–24.0 Final slightly high-angle wide shot. The referee brings the bulldog to the center and raises one arm. Red-and-white paper streamers fly into the ring. Vintage photographers fire flashbulbs and strong white strobes. The crowd remains standing, shouting, clapping, whistling, and waving hats. The handheld camera slowly pushes closer until the final frame.
- Three reference images are each assigned one job — character, character, environment — so nothing gets blended.
- The instruction never make him realistic is repeated as a hard constraint, which is what holds the mixed-media split.
- Sports broadcast framing gives the model a familiar camera language for cutting between two very different subjects.
Cyber Skydive Freefall Cut Sequence
A freefall from a spire cut every two to three seconds, with one identity reference and a single continuous sky environment holding it together.
Prompt IDENTITY: @Image1 supplies identity only — face, long black hair, low-brim cap, glossy black bodysuit, segmented cybernetic right arm, circuit tattoos, heeled boots. Frame is one continuous open-sky environment edge to edge. Cuts every 2-3s, no shot over 3s, one camera movement per shot. 0-2s | Worm-eye far below, whip tilt up as she pushes off the spire ledge. [Cut] 2-4s | Macro on her heel leaving the lip, static. [Cut] 4-6s | Top-down on her back, falling with her, hair rips straight up. [Cut] 6-8s | Boot macro, black plates streak in and latch over her shins, static. [Cut] 8-10s | Side track, thigh and hip plates snap shut. [Cut] 10-12s | Cybernetic arm macro, forearm plating extends over it, static. [Cut] 12-15s | Wide, chest harness clamps on, two stabilizer fins fold from her back, push-in. [Cut] 15-17s | Face close-up, a thin dark visor slides from the cap brim over her eyes, locked. [Cut] 17-20s | Extreme wide, geared figure punches the cloud layer, twin vapor spirals. [Cut] 20-23s | Head-down delta dive, fins biting air, hard push-in on her back. [Cut] 23-26s | Ground-level low angle, she swells in frame fast. [Cut] 26-28s | She lands in a deep crouch, cybernetic arm braced on stone, cracks radiate 4m in a spider-web pattern. [Cut] 28-30s | 0.4x slow motion, concentric shockwave ripple distorts the air outward, dust erupts to waist height, she rises into a recovery stance. GEAR: plates arrive as fast streaks from off-frame, each locking with a latch snap and a thin amber seam that fades in 0.4s and lights her skin. Assembly runs 6-17s, one region per shot. PHYSICS: terminal velocity, hair and fabric dragged upward, motion blur on background only, subject sharp, faster after 17s. AUDIO: wind roar climbing, latch snap on each lock, sub-bass on every cut, half beat of silence at 25.5s, air-pressure boom at 26s, rumble tail. STYLE: painterly anime illustration matching @Image1, cel-and-gradient shading, cool desaturated sky.
- The reference is explicitly limited to identity, leaving the model free to stage motion without copying the source frame.
- One movement per shot and a hard three-second ceiling keep a fast-cut sequence from becoming incoherent.
- Declaring one continuous environment edge to edge means the cuts never need to re-establish where we are.
WWI Dogfight with Layered Cinematography
A 21:9 WWI aerial battle where every shot specifies focal length, aperture and a distinct foreground, midground and background layer.
【30 秒一战空战 严格分层镜头版提示词（逐镜头标注摄影参数 + 前景 / 中景 / 背景三层光影，防过拟合） 30 秒高镜头密度一战空中格斗完整故事线，激烈战场硝烟氛围，一战高空漫天混战场景，超大画幅宽银幕，粗颗粒复古胶片质感，黄褐色复古战场影调，21:9 宽银幕，画面全程动态流畅无卡顿，每一个镜头严格区分前景 / 中景 / 背景三层景深，前后景焦距完全不同，杜绝平面前后景同焦画面，彻底避免 AI 过拟合同质化效果。德国双翼战机  德国战机2 ，英国双翼战机  英国战机 ，德军飞行员  德飞行员 ，英国飞行员  英飞行员 。 0-2s：大远景高空俯视 焦距：14mm 光圈：f/5.6。前景：浓密高空硝烟缓慢流动擦过镜头下缘；中景：两架主角双翼战机（德方战机  德国战机2 在后，英方战机在前  英国战机 ）一起在云缝里高速俯冲，后机死死咬住前机尾后；背景：数十架一战士战机群在远方天空各处缠斗，拉出密密麻麻白色航迹，厚重铅灰色积云铺满整个天空。自然光硬侧光，光线从侧上方斜切下来，硝烟边缘被阳光打透成半透明金色。 2-4s：驾驶舱中景跟拍 焦距：75mm 光圈：f/2.0。前景：螺旋桨转动拉出动态模糊气流从镜头前扫过；中景：德方飞行员  德飞行员 坐在驾驶舱里猛推操纵杆，头盔风镜反射出前方英方战机轮廓；背景：战机帆布蒙皮机身结构、高空远处模糊的云团轮廓层次虚化。侧逆光打亮飞行员肩线，驾驶舱内部保留暗部细节，浅景深背景完全虚化。 4-7s：机身侧面跟拍中近景 焦距：50mm 光圈：f/2.8。前景：高速气流卷动机翼蒙布线头抖动擦过画面边缘；中景：两架飞机机翼几乎贴在一起，德方战机机枪口连续喷吐出枪口焰，亮白色曳光弹线条连续擦过英方战机机翼蒙皮表面；背景：远处空中其他战机开火的微弱枪口焰光点零散分布在硝烟里。侧顶硬光，机枪开火瞬间枪口焰在机身蒙皮上投下跳动的光斑。 7-10s：机翼破口大特写 焦距：180mm 光圈：f/1.4。前景：飞溅的金属蒙皮碎屑在镜头前景慢动作划过；中景：英方战机机翼表面被机枪子弹击中，帆布蒙皮撕开破口漏出内部钢丝骨架，缕缕白烟从破口处冒出来；背景：远处蓝天和云层被浅景深完全虚化成柔和色块。侧光精准打亮破口边缘撕裂的帆布纤维纹理，暗部保留阴影层次，极致浅景深。 10-13s：飞行员近景特写 焦距：85mm 光圈：f/1.8。前景：高速气流吹动飞行服领口在画面左下角微微晃动；中景：英方飞行员猛拉杆回头看向后方，脸上紧绷全神贯注，快速扳动操纵杆做极限规避动作；背景：驾驶舱风窗外飞速流过的云层完全虚化。侧光半打亮飞行员半张脸，另一半落在硬朗阴影里，浅景深背景完全模糊，突出人物紧绷情绪。 13-17s：极限规避低角度环绕镜头 焦距：24mm 光圈：f/4。前景：地面炸起的橙色硝烟烟尘从画面底部向上翻涌；中景：英方战机侧身几乎 90 度侧翻，大角度转向从德方战机射击窗口里快速滑脱，机翼下方掠过地面一战战壕铁丝网轮廓；背景：远方地平线处数十个地面炸开的硝烟烟柱缓缓升起。侧逆光把战机机身勾出完整金色轮廓，低角度让机身在天空里极具冲击力，中景深只把机身主体拍实，远景硝烟层次自然虚化。 17-21s：高空拉升大远景 焦距：20mm 光圈：f/8。前景：半透明硝烟云团从镜头前缓缓飘过；中景：两架主角飞机一追（德方战机）一绕（英方战机）在高空云团里拉出交叉的白烟轨迹；背景：整片天空布满上百条战斗机拉出的白色航迹线，无数小黑点大小的战机在远景各处互相厮杀，庞大混乱的一战空战战场全貌完整铺开。顶光漫射下硝烟层次丰富，大景深完整收纳前景中景背景三层全部清晰的战场空间，画面纵深感拉满。 21-24s：迎头对冲低角度仰拍 焦距：35mm 光圈：f/2.8。前景：两架飞机高速旋转的螺旋桨扇叶边缘虚化形成动态扇面；中景：双机同时迎头对冲相向飞行，机身快速向镜头逼近，距离飞速缩短；背景：后方整片高空混战的机群轮廓全部虚化散焦。正仰拍逆光，机身被阳光完全勾勒出黑色剪影，只透出机翼轮廓的半透明帆布纹理，前景螺旋桨动态模糊增加速度感。 24-27s：隔舱对视大特写 焦距：100mm 光圈：f/1.4。前景：驾驶舱风窗外晃动的气流波纹虚化在镜头前；中景：两名飞行员隔着呼啸气流在驾驶舱里互相对视一瞬，时间微微放慢；背景：两侧飞速向后流走的天空和云团完全虚化成运动模糊拖影。侧软光只打亮两名飞行员半张脸，背景极致虚化，浅景深把所有注意力锁在人物眼神对视的瞬间。 27-29s：贴脸擦身极高速跟拍 焦距：40mm 光圈：f/3.5。前景：机翼尖擦过的气流扰动在画面边缘形成动态扭曲波纹；中景：两架战机几乎贴脸擦肩而过，机翼尖差几厘米就会相撞，气流吹动机翼表面蒙布剧烈抖动；背景：两侧向后飞速退去的混战战机全部拉出动态运动拖影。追焦跟拍全程只有两架主角战机机身完全锐利，前后运动物体全部带自然运动模糊，速度感拉满。 29-30s：两机反向散开收束大远景 焦距：21mm 光圈：f/5.6。前景：最后一缕高空硝烟缓缓从画面中间飘过；中景：两架反向飞远的双翼机背对着彼此向天空两个方向散开，身后留下两道漫长的白烟航迹，黄昏阳光把机身轮廓镀上一层金边；背景：远方天空仍在持续厮杀的整个战场，漫天航迹和硝烟构成庞大的一战空战史诗全景。黄昏暖橙色侧逆光斜照整个画面，烟的边缘是金的，云层底部是暖橙色，远处战场硝烟带着冷蓝灰调，冷暖对比宽银幕史诗感拉满。 全局约束：全程动作节奏紧凑激烈，一战战机细节完全写实，没有任何现代喷气式飞机，无多余字幕无多余文字，胶片颗粒均匀自然，所有镜头的光圈焦距参数对应生成正确景深分层，严格杜绝前后景同焦平面的扁平化画面，完全避免过拟合 AI 同质化效果。镜头要自然，不要生硬。】全片不要有音乐，不要有文字。
- Per-shot focal length and aperture force genuinely different perspectives instead of one look repeated.
- Requiring three separated depth layers per shot is a direct countermeasure to the flat, same-focus frames models default to.
- Assigning named aircraft and pilots to each side keeps the combatants distinguishable through the smoke.
Anime Opening Continuous Flythrough
A dark-fantasy anime opening that replaces fast cutting with one unbroken roller-coaster camera sweeping past each character in turn.
type: anime_opening_continuous_camera_flythrough style: visual: dark fantasy anime, cel-shaded 2D, high contrast, full-color Japanese anime motion_quality: 24fps, 作画枚数多め, メリハリのあるスピードランプ tone: stylish, dramatic, kinetic, elegant, ominous direction: > 日本のフルカラーアニメのオープニング。 高速なカット割りの代わりに、一筆書きのような連続カメラワークで、 複数のキャラクターを次々と捉えていく。 カメラは右へ左へ、上下へ、奥へ手前へと飛び回るローラーコースターPOVで、 一切止まらず、各キャラクターの最も映える瞬間を連続的につないでいく。 各キャラクターのポーズ・表情・背景・空間演出は、 そのキャラクターの性格、武器、属性、感情の核、物語上の役割から 最も魅力的に見える形をAIが自律的に判断して構成すること。 camera: motion: fast forward dolly with lateral drifts, rollercoaster POV, fluid aerial movement core_rule: > no hard cuts, no static frames, no fades. 全編を通して一続きのワンカットとして成立させること。 speed_ramps: > キャラクターのリビール直前に減速し、決めの瞬間で一瞬だけ視認性を確保し、 通過と同時に再加速する。 lens_feel: dynamic anime cinematography, dramatic perspective shifts, strong parallax final_exception: > ラストのクライマックスキャラクター、または集合決めカットの直前のみ、 重みを出すために初めてカメラの運動を極端に緩める、 もしくは短く静止してもよい。 environment_logic: base_space: 無限に広がる異空間ヴォイド variation_rule: > 各キャラクターのリビール区間ごとに、そのキャラクターの属性、感情、 象徴、戦闘スタイル、役割に最も合う環境要素をAIが選んで構成すること。 同じ空間を繰り返さず、毎回異なる空間的印象をつくること。 ただし全体としてはひとつの連続した異空間を飛行している感覚を保つこと。 palette_options: - deep crimson (#5A0000–#8B0000) + cyan mint accents + black shadows - midnight blue void + white petals + silver light - blood red mist + black feathers + gold rim light - violet smoke + shattered glass + cold cyan - 上記をベースに、各キャラクターに合わせて自由に再解釈してよい floating_elements_pool: - petals - feathers - blades - ribbons - chains - shattered glass - ash - sparks - torn paper - ink splashes - crystals - smoke - water droplets - leaves lighting: > dramatic rim light, deep shadows。 光源設計はキャラクターの性格や役割に応じて変えること。 支配的なキャラには逆光や王者のような縁光、 儚いキャラには拡散光、 狂気のあるキャラには不安定な明滅光など、 感情の印象を光で補強すること。 input_characters: description: > 以下にキャラクターのリストを与える。 人数は固定しない。2人でも10人以上でも対応可能。 各キャラクターについて、名前・性格・武器・属性・役割・感情の核・象徴モチーフなどを参照し、 そのキャラらしさが最大化する一瞬を構成すること。 format_example: - name: Character Name role: protagonist / rival / villain / mentor / key figure / support personality: "" weapon_or_power: "" attribute_or_theme: "" emotional_core: "" symbolism: "" priority: high / medium / low reveal_planning: global_rule: > 入力された全キャラクターを、物語の高まりが自然に増していく順に並べ替えてよい。 基本的には、軽め・不穏・謎めいた導入から始まり、 中盤で躍動感と情報量を増し、 終盤で主人公・対立軸・ラスボス・最重要人物へ向けて熱量を上げること。 per_character_rule: > 各キャラクターごとに以下を自動で設計すること： 1. pose: 静止ではなく「動きの最中の一瞬」 2. expression: 感情の核が伝わる表情 3. framing: 最も映えるカメラ距離・角度 4. background_variant: そのキャラに対応した空間演出 5. foreground_wipe: 次のキャラへつなぐ前景通過物 6. motion_relation: カメラに対して向かってくる / すれ違う / 見下ろす / 落下する / 回転する 等 uniqueness_rule: > 各キャラクターで、体勢、シルエット、画面構図、視線方向、背景モチーフ、 前景の抜け、動きのベクトルを被らせないこと。 連続して似た演出を使わないこと。 duration_rule: > 各キャラクターの見せ尺は均一でなくてよい。 priority が高いキャラクターほど、わずかに長く、印象的に見せること。 低優先キャラは短く鋭く見せ、高優先キャラは減速を強めて存在感を出すこと。 character_processing_loop: instruction: > 入力されたキャラクター配列を上から順に機械的に処理するのではなく、 オープニング映像として最も気持ちよく流れる順番に再構成してよい。 それぞれについて以下を判断して映像化すること。 for_each_character: decide: - このキャラは支配的か受動的か - 攻撃 / 防御 / 逃走 / 佇み / 観察 / 詠唱 / 指揮 のどれが最も似合うか - 武器や能力をどう一瞬で象徴的に見せるか - 視線、手、指、髪、衣装、武器のどこを強調すべきか - カメラがそのキャラに向かうべきか、横切るべきか、追い抜くべきか - そのキャラに最も合う背景と前景モチーフは何か output: - pose - expression - framing - background_variant - foreground_wipe - transition_vector transitions: between_reveals: > 花弁、羽根、刃、リボン、鎖、ガラス片、煙、灰、インクなどが 必ずレンズ手前を至近距離で横切り、それをワイプ代わりにして次のキャラへつなぐこと。 rule: > 必ず「前景がレンズを横切る → 空間が変化する → 次のキャラが現れる」 という流れを守ること。 continuity: > 前景ワイプは単なる切り替えではなく、 カメラが本当に次の空間へ飛び込んでいく感覚を生むように使うこと。 climax_logic: final_focus_rule: > 最後の区間では、最重要キャラクター （主人公 / ラスボス / キーパーソン / 物語の中心人物）に到達すること。 そのキャラは他よりも重く、強く、象徴的に見せること。 ending_options: - 最重要キャラクター単体でカメラが初めて止まり、一枚絵として決まる - 主人公の先に最大の敵が現れ、緊張感のある静止に入る - 最重要キャラのあと、短く複数人の集合構図へ流れ込み、一枚絵で締める final_image_rule: > ラストはポスターのように成立する構図にすること。 それまでの流動性と対比して、最後にだけ「止まる意味」があるように演出すること。 output_goal: > 結果として、全体が一本の連続したアニメOPショットとして成立し、 各キャラクターが短時間でも明確に識別でき、 しかも一人ずつ違う魅力で刻み込まれること。 単なる紹介映像ではなく、「この作品世界の熱量と因縁」が伝わること。 negative: - hard cuts - static camera (except final climax hold) - fades - text - logos - subtitles - photorealism - 3DCG look - repetitive poses - repeated environments - flat staging
- Replacing cuts with a single continuous camera is stated as the core direction, so the model does not fall back on montage.
- Each character's pose and staging is delegated to the model from their personality and role, which keeps the roster varied.
- A structured header — type, style, motion quality, tone — reads like a spec sheet the model can follow top to bottom.
Wuxia Inn Duel Over One Bun
Two swordswomen wreck an entire period inn fighting over the last steamed bun, mixing slow motion with rapid cutting.
【风格】武侠电影级动作喜剧（Wuxia Action Comedy），古风客栈实景，8K，达芬奇高级调色，升格慢动作与快剪结合，真实布料与木屑物理，横屏16:9 【时长】30秒 【场景】古风江湖客栈大堂，木桌长凳、红灯笼、蒸笼冒热气，梁柱交错，光从窗棂斜射带浮尘 【角色】女侠A @图1（红衣冷艳，用剑）、女侠B @图2（青衣飒爽，用双筷/软鞭），两人武艺相当 [00:00-00:02] 钩子·同时出手 蒸笼掀开——热气散去，只剩孤零零一个白胖包子。两只手"唰"地同时探向它，在包子上方一寸僵住。镜头拉近两人对视，杀气骤起。 音效：蒸汽"嘶"声，一声兵刃出鞘。 [00:02-00:06] 拔剑·桌面开打 A拔剑挑翻整张桌子腾空，B踩着飞起的长凳跃上房梁，包子被气浪震到空中。碗筷茶壶四散飞溅。 [00:06-00:11] 空中争夺（升格） 包子在半空划弧，两人凌空交手，A剑尖挑、B筷子夹，包子在刀光间被抢来抢去，谁也没碰实，热气还在包子上冒。 [00:11-00:16] 客栈大乱 战场蔓延，两人踩桌翻梁、灯笼被削落、木屑纷飞，其他"食客"抱头躲桌下。包子始终在两人争夺中心悬着不落。 [00:16-00:21] 决胜一击（升格特写） A与B同时使出绝招，剑气与鞭影在包子两侧交汇——包子被劲气托着高高弹起，两人各自摆出接杀造型，屏息等它落下。 [00:21-00:26] 神反转 镜头跟着下落的包子——一只慵懒的橘猫"喵"地从桌上跃起，在半空一口叼住包子，稳稳落地，当着两人的面吧唧吧唧吃完，舔爪。 音效：所有打斗音效戛然而止，一声"喵~"，乌鸦飞过。 [00:26-00:30] 傻眼收尾（定格） A和B保持着帅气的接杀姿势僵在原地，剑和筷子还举着，齐刷刷看向吃饱打嗝的猫，表情裂开。 字幕（砸出）：「有些仗，打赢了也没用。」 音效：一记喜剧"咚"，猫满足地打了个嗝。 【导演备注】1.反差铁律：打斗越是天崩地裂、招式越华丽正经，最后被猫截胡的落差越好笑；2.身份锁定：A=@图1红衣用剑、B=@图2青衣用筷/鞭，脸/服装全程一致；3.节奏：2秒对峙→拔剑→空中争夺→大乱→决胜→猫反转，动作段用快剪+关键处升格；4.物理真实：包子热气、木屑、灯笼、布料惯性、猫的重量都要真实，武侠不卡通；5.包子必须全程在画面中心被争夺，是视觉焦点和笑点核心；6.不见血、不伤人，纯招式对拆。 【负面提示词】卡通武侠，塑料CG，换脸，两人身份/武器混淆，包子中途消失，猫出现得太早，血腥伤人，多余手指，字幕提前，水印，真实品牌logo，画面糊乱，未成年人形象。
- A trivial prop as the object of the fight sets the comic tone without a single line of dialogue.
- Alternating overcranked and fast-cut beats gives the choreography a rhythm rather than uniform speed.
- Steam, wood splinters and falling lanterns provide physical debris that tracks the escalation.
Shadow Blade Dance Combat
Contemporary dance flows directly into single-katana strikes while shadow matter forms predatory silhouettes around the performer.
High-end cinematic 3D realism fused with rapid contemporary dance and spectral blade combat. Explosive turns, deep backbends, floor slides, aerial contractions and sharp limb extensions flow directly into precise single-katana strikes, creating choreography that feels graceful, feral and impossibly fast. Dense shadow matter forms predatory silhouettes, lunging smoke trails and collapsing black shockwaves, while every blade arc tears crimson fabric-like energy through the air and disintegrates impacts into ink-dark particles. Aggressive orbiting camera movement, low-angle tracking, extreme foreshortening, sudden lateral acceleration, cold volumetric haze and wet reflective surfaces amplify the performance without sacrificing silhouette clarity. Realistic cloth dynamics, controlled motion blur, physical blade weight and feature-film rendering preserve elegance, danger and scale. The performance begins mid-attack as a shadow wolf leaps through the smoke and the dancer @[character ref] folds beneath it in a violent backbend, drawing her single katana through its body during the recovery. More wolves circle and attack from every direction as she accelerates through spins, floor sweeps, aerial kicks and whipping turns, each movement becoming a clean blade strike that shreds them into black vapor and crimson fragments. The camera spirals through the pack with her, ending in full motion as she launches into another rotating slash against the final wave.
- Dance vocabulary and combat vocabulary are fused in one sentence, so the model blends them rather than alternating.
- The shadow effect is given physical behaviour — lunging, collapsing, trailing — instead of being described as a look.
- Crimson energy arcs give every blade movement a visible trace, which keeps fast choreography readable.
Hulao Pass Three Kingdoms Duel
A mounted three-way duel at Hulao Pass where the references supply identity only and their studio backgrounds are explicitly discarded.
--------------- Duration: 20s | 16:9 | 24fps Duel from Romance of the Three Kingdoms, battle at Hulao Pass, late Han dynasty. REFERENCES Image 1 — 呂布 LU BU Image 2 — 関羽 GUAN YU Image 3 — 張飛 ZHANG FEI Use them for IDENTITY ONLY: face, beard, hair, headwear, armour, cloak colour, build, proportions. IGNORE their white studio background, flat studio lighting and standing pose — none of it appears here. Every shot is outdoors, and all three men are mounted and fighting. STYLE (all beats) A dusty plain before a huge stone mountain pass at dusk. Two vast armies on either side, banners rippling, dust in the air. Overcast sky, low copper sun breaking through. Palette: iron grey, ochre dust, blood red, bronze. Desaturated and earthy. 50mm, shallow focus, heavy haze, film grain, high contrast, hard rim light through the dust. Photorealistic historical epic, sweat and grime, worn scratched armour. No fantasy glow, no magic. WEAPONS — no reference exists. Build from this, keep identical throughout. Each is 1.5x its owner's height. Never swap them. 呂布: ji halberd — straight spear point, one crescent side blade below it on one side, long dark shaft, bronze fittings. 関羽: guandao — one heavy broad curved blade with a hook on its back edge, joined to a long dark shaft by a bronze dragon head. 張飛: serpent spear — slender steel blade forged in an S-shaped wave, on a plain dark shaft bound with cord. HORSES — no reference exists. Anatomically correct, four legs, correct joints. 呂布: large red-chestnut stallion, black mane, bronze fittings, red tassels. 関羽: tall dark bay, black mane and lower legs, plain leather tack. 張飛: heavy solid black, thick neck, shaggy fetlocks, battered iron tack. BEAT 1 (0-4s) 呂布 — clean-shaven, gold headdress with two pheasant feathers, red cloak, halberd, red-chestnut horse — sits alone between the two armies, halberd across his saddle. The horse stamps and turns a half step. He raises the halberd and levels it at the enemy line. Camera: WS from low, slow push-in. BEAT 2 (4-8s) 張飛 — bristling beard, black iron armour, dark cloak, serpent spear, black horse — bursts from the line at a gallop, roaring, and drives the spear at 呂布. 呂布 turns the halberd across his body and knocks it aside. Sparks and dust. The horses wheel past each other. Camera: tracking alongside at horse height, moving with the charge. BEAT 3 (8-12s) 関羽 — long smooth black beard, ruddy face, dark green robe over armour, green headwrap, guandao, dark bay horse — rides in from the far side, rises in the stirrups and cuts down overhead. 呂布 catches it on the haft. Both strain, blades locked, horses shoulder to shoulder. Camera: MCU, orbiting once around the locked weapons. BEAT 4 (12-16s) All three circle in churning dust, weapons striking and turning each other aside, horses rearing. 呂布 in red and gold, 関羽 in green, 張飛 in black iron. Cut tight to 呂布's eyes under the headdress — narrowing, calculating, uncertain for the first time. Camera: handheld, close, drifting between them. BEAT 5 (16-20s) 呂布 wrenches his horse around, sweeps the halberd once to drive them back, and gallops for the pass, red cloak and feathers streaming. 関羽 and 張飛 pull up side by side, chests heaving, weapons still raised, watching him go against the low copper sun. Camera: WS, pulling out to reveal both armies. AUDIO War drums and massed shouting throughout, rising through beats 2-4. Hooves on dry earth, snorting horses, steel ringing on steel, creaking leather, wind and dust. A deep roar from 張飛 at 4s. Near-silence for a breath at 12s on 呂布's eyes, then the clash returns. No dialogue. AVOID white studio background, flat studio lighting, seamless backdrop, neutral standing poses, facial hair on 呂布, on-screen text, subtitles, watermarks, modern objects, fantasy glow, magic, wire-work floating, clean unworn costumes, faces/armour/weapons swapping between beats, weapons changing shape or length, horses with deformed or extra legs, extra or missing limbs, more than three warriors, mixed camera moves, jitter, flicker, ghosting.
- The prompt lists what to take from each reference and what to ignore, which prevents studio lighting leaking into the battlefield.
- Stating that all three are mounted and outdoors in every shot removes the standing-pose default from the source images.
- Named historical figures give the model a strong wardrobe and silhouette prior to work from.
Breaking the Formation on a Rainy Night
A Chinese-inspired dark-fantasy combat short in AAA game style, with the reference image locked as the single source of truth for the opening frame.
Execute immediately. Do not restate the prompt, preface the output with a capabilities statement, or offer alternative concepts. Create an original, Chinese-inspired dark-fantasy combat short in a AAA game style titled “Breaking the Formation on a Rainy Night.” Deliver 16:9 landscape, 720p, exactly 30 seconds, with generated audio synced to picture. Reference locks: @Image 1 is the single source of truth for the opening frame: composition, the characters’ screen-left/screen-right placement, character scale, spacing, camera position, and lighting. @Image 2 locks the hero, Qinglei Jianzhu (“Azure Thunder Sword Adept”): same face, silver-white high ponytail, build, white/red/black lightning-pattern armor, blue-white lightning motifs, and a single straight sword. @Image 3 locks the boss, Rongjia Yanjiang (“Molten-Armor Nightmare General”): same square bronze mask, two small horns, orange eyes, massive build, black molten armor, and a single two-handed greataxe. @Image 4 locks the location for the entire piece: one rain-soaked old Chinese street, buildings on both sides, a distant pavilion, warm lanterns, wet flagstones, and cool-blue ambient light. Keep exactly these two characters on this same street for the full 30 seconds. Lock identity, face or mask, wardrobe, scale, and weapons across every shot. Keep Qinglei Jianzhu on screen left and Rongjia Yanjiang on screen right throughout the action. Maintain the 180-degree rule—no unmotivated teleports or side swaps. Sell weight, inertia, contact, and equal-and-opposite reaction. Every move must play through wind-up, acceleration, impact or dodge, follow-through, and a clean settle. 0–5 seconds: Open on the quiet standoff from @Image 1. Steady, moderate rain; lanterns sway slightly. Rongjia Yanjiang takes two slow steps forward. Each heavy footfall kicks water out of the puddles while the greataxe blade drags across the wet flagstones, throwing a few dark-gold sparks. Qinglei Jianzhu shifts her rear foot half a step and raises the straight sword into a firm guard. Dolly slowly forward roughly one meter along the street centerline, then settle into a locked frame by 00:05. 5–11 seconds: Side medium-wide. Rongjia Yanjiang drops a shoulder for the wind-up, then drives one clean horizontal sweep with the single greataxe. Qinglei Jianzhu does not plant and hard-block. She retreats on a diagonal and meets the outer edge of the axe blade at an angle with her single straight sword, redirecting the force. Show exactly one brief, readable sword-to-axe contact and a small burst of metal sparks. Sell the power difference through both characters’ arms, torsos, and footwork: Qinglei Jianzhu is driven back two steps before regaining her base; Rongjia Yanjiang carries the sweep through its full follow-through and settles. Track laterally for a short distance, then lock off as both characters come to rest. 11–18 seconds: Low-angle wide. Rongjia Yanjiang raises the greataxe overhead with both hands, drops his center of gravity to load the strike, then slams the blade straight down into the wet flagstones. Qinglei Jianzhu pushes off toward back-left before impact—no roll, no disappearance. Trigger the effects only after the blade hits: cracks radiate from that single impact point, a low dark-gold shockwave runs across the street, puddles kick outward, and the rain briefly flashes into a thin veil of steam. The shockwave edge carries Qinglei Jianzhu into a longer backward slide. She plants the sword tip against the street as a brake and stabilizes. End with Rongjia Yanjiang’s greataxe visibly buried in the ground. Use one impact shake on contact, then return to a stable frame. 18–25 seconds: Qinglei Jianzhu triggers her one signature move, “Qinglei Pozhen.” Blue-white current runs from the lightning motif on her right shoulder, down the arm, and into the straight sword; the lightning veins inside the blade intensify. Raindrops and shallow puddle water lift briefly into one thin ring around her without covering her face or body. Keep her fully visible as she makes one continuous, readable dash on a low arc, cutting in from outside Rongjia Yanjiang’s axe arm to his front-left. No teleport, clone, or second human silhouette. Rongjia Yanjiang tries to wrench the greataxe free, but the ground still holds it. Follow Qinglei Jianzhu from a rear three-quarter angle for a limited distance, keeping both full bodies and both weapons in frame throughout. 25–29 seconds: Qinglei Jianzhu exits the dash, plants cleanly, and completes one short upward sword recovery. The sword tip comes to a precise stop against the center crack in Rongjia Yanjiang’s square mask, making only light contact. Do not hit the greataxe again. On that exact contact beat, drop one vertical blue-white lightning bolt from the top of frame into the straight sword, then carry the charge through the tip into the boss’s mask and chest plate. Push the rain curtain and puddles outward in one ring. The dark-gold fissures in the black armor flash blue-white, then fade quickly. Build every effect from the sword-tip contact point. Keep Qinglei Jianzhu’s face, Rongjia Yanjiang’s mask, both characters’ hands, and both weapons unobscured and readable. 29–30 seconds: Let all intense light fall off quickly and let the rain resume falling naturally. Qinglei Jianzhu holds the final sword pose on screen left. Rongjia Yanjiang holds on screen right with the greataxe still buried in the ground. Neither character moves. Hold on a fully locked-off shot for at least one full second—no push-in, rotation, or drift. Build one continuous generated soundtrack, synced to picture: steady but restrained rain, low distant thunder, footsteps on wet flagstone, axe blade scraping on flagstone, the greataxe whoosh, one sword-to-axe metal hit, the greataxe impact, cracking stone, puddles surging outward, blue-white electrical current, and the vertical lightning strike. Underscore it with restrained low war drums. Every transient must land on the matching contact or landing beat. No dialogue, shouts, voice-over, lyrics, or chanting. Do not restart the ambience or score midway through the clip. Art direction: an original, Chinese-inspired dark-fantasy action-game aesthetic with realistic cinematic lighting, clearly rendered rain, and strong material definition for metal, leather, fabric, and wet flagstone. Keep exactly two characters. No face swaps, costume changes, location changes, scale changes, or changes in weapon count. No extra hands or feet, extra swords, extra greataxes, clones, summons, wings, aerial combos, or screen-filling particles. The straight sword and greataxe may not shorten, duplicate, morph, or pass through either body. No HUD, on-screen text, subtitles, or logos. No 360-degree orbit and no camera roll. Every camera move must resolve and lock at the end of its action beat.
- Designating one image as the truth for composition and screen positions removes ambiguity about where everyone starts.
- Asking for generated audio synced to picture makes sound a deliverable rather than a byproduct.
- Opening with execute immediately keeps the model from spending output on restating the brief.
Floating Magic City FPV Anime
A high-speed FPV flight through a floating magic city, where every cut is hidden by a whip pan or motion-blur match instead of a hard cut.
SUBJECTS: セレスティア（Celestia）、闇の魔導師 @ image1。銀白色から淡いラベンダーへとグラデーションする長い髪、幻想的に輝く紫色の瞳を持つ優雅な闇の魔法使い。発光する紫のクリスタル装飾が施されたゴシック調の黒いドレスをまとい、宙に浮かぶ紫のクリスタルコアを頂いた洗練された黒い魔法の杖を携える。 ENVIRONMENT: 雲の上に浮かぶ壮大な魔法都市。浮遊島、石造りの空中橋、魔法使いの塔、巨大なクリスタル尖塔、空中に浮かぶ書店、魔法カフェ、飛行船、浮遊庭園、上向きに流れる幻想的な滝、浮遊ランタン、魔法の樹々が広がる幻想世界。 CAMERA（全体）: 全編を通してスピード感のあるシネマティックFPV視点。各カットでは「1つの主要カメラワーク」のみを採用し、演出を整理。カット間はホイップパンやモーションブラー・マッチカットで自然につなぎ、ハードカットは使用しない。 STYLE: 最高品質のアニメシネマティックスタイル。超高品質イラスト、鮮やかなファンタジーライティング、美しいセルシェーディング、力強いアニメ線画、絵画的ハイライト、幻想的なブルーム、ボリューメトリックゴッドレイ、魔法のレンズフレア、AAA級ファンタジーアニメのオープニング品質。 COLOR LOGIC: 漆黒、ミッドナイトブルー、バイオレット、ラベンダー、輝くマゼンタ、純白のハイライト、淡いシアンの環境光、暖かなゴールドのランタン光、エメラルドグリーンの植物。魔法エフェクトは深い紫を基調とする。 ━━━━━━━━━━━━━━━━━━━━━━ TIMELINE（合計30秒） ━━━━━━━━━━━━━━━━━━━━━━ 0:00-0:05【静止 → 爆発的始動】 MAIN FX：巨大な魔法陣1つのみ セレスティアは時計塔の頂上で静かに立ち、マントと髪が風になびく。魔法の粒子が漂う中、杖を掲げると足元に巨大な魔法陣が展開する。 CAMERA： ゆっくりとしたオービット → 急激なスピードランプ TRANSITION： モーションブラー・マッチカットで屋根上チェイスへ SFX： 魔力の低い唸り、クリスタル共鳴、魔力爆発、突風 ━━━━━━━━━━━━━━━━━━━━━━ 0:05-0:10【疾走】 MAIN FX： 足元に生成される発光魔法足場のみ 屋根の上を高速で駆け抜け、一歩踏み出すたびに足元へ魔法の足場が出現し、それを蹴って次々と跳躍する。他の魔法演出は重ねない。 CAMERA： FPV追跡、足元中心のローアングルトラッキング TRANSITION： 大きく跳躍しながら上方向へホイップパン SFX： 魔法の足音、魔力バースト、風切り音 ━━━━━━━━━━━━━━━━━━━━━━ 0:10-0:16【静止 → ポータル連鎖】 MAIN FX： 転移ポータル 空中で約0.4秒だけスローモーション。周囲が静まり粒子だけがゆっくり漂う。その直後、高速で複数の転移ポータルを連続通過する。 CAMERA： スローモーション静止 → ポータル回転に合わせた高速オービット TRANSITION： ポータルの白い閃光で街への急降下へ SFX： （0.4秒ほぼ無音） → ポータル共鳴、クリスタルベル、空間歪曲音 ━━━━━━━━━━━━━━━━━━━━━━ 0:16-0:21【急降下魔法】 MAIN FX： 街全体を照らす巨大ルーン1つ ランタンが並ぶ街路へ急降下しながら巨大魔法を発動。街全体が紫色の光で照らされる。蝶やリボンは背景演出程度に留める。 CAMERA： 急降下ショット＋クローズアップ＋ワイド俯瞰を交互に使用 TRANSITION： スピードランプでラストスプリントへ SFX： 多層魔法詠唱、クリスタルベル、魔法爆発 ━━━━━━━━━━━━━━━━━━━━━━ 0:21-0:27【クライマックス】 MAIN FX： 巨大衝撃波 最後の全力疾走。クリスタル尖塔へ跳躍し空中で一回転。着地と同時に杖を地面へ突き立て、都市全体へ巨大な魔力衝撃波が広がる。この瞬間のみ演出を最大化する。 CAMERA： 空中回転中はオービット → 着地後は都市全景へ大きく引く TRANSITION： ワイドショットを維持しながら衝撃波の光が徐々に消えていく SFX： 壮大な魔法クレッシェンド、クリスタル噴出音、オーケストラのインパクト ━━━━━━━━━━━━━━━━━━━━━━ 0:27-0:30【余韻】 MAIN FX： 残光のみ セレスティアは尖塔の頂上に静かに立ち、衝撃波から舞い降りる光の粒子がゆっくり降り注ぐ。タイトルやロゴを配置できる余白として使える締め。 CAMERA： ゆっくりとしたプッシュイン → 静止 SFX： 消えていくクリスタル共鳴、静かな魔力の余韻
- Allowing only one camera move per shot keeps a fast FPV sequence from becoming visually noisy.
- Banning hard cuts and naming the transitions that replace them keeps the flight continuous.
- The city is described as an inventory of landmarks — bridges, towers, airships, upward waterfalls — giving the flight things to pass.
Mecha Motorcycle Rain Chase
A timestamped storyboard for a mecha-motorcycle sprint through a downpour, with water displacement and plasma trails specified as physics directives.
[Timestamped Script & Storyboard] [00:00 - 00:08] [High-Speed Dash] — Cutting Through the Wind | Action / Physics Directive: The camera flies in close pursuit, positioned just behind and to the side of the mecha-motorcycle as it races through a downpour. Its wide, rapidly spinning tires kick up massive sheets of water several meters high, while the blue plasma exhaust trail etches a long streak of light against the rainy night. Subtext: Convey a sense of extreme speed to the AI; focus the visual composition on the physical interaction between the rain, reflections on the wet road, and the engine exhaust. [00:09 - 00:16] [Extreme Evasion] — Center of Gravity Shift | Action / Physics Directive: The camera instantly shifts to a high-angle overhead shot. A series of exploding, wrecked vehicles suddenly blocks the path ahead; the mecha-motorcycle leans sharply—almost scraping the ground—as its tires generate dazzling orange sparks from friction, executing a tight "S-curve" to perfectly weave around the burning wreckage. Subtext: Illustrate the shift in the mecha's center of gravity during high-speed movement, highlighting the gravitational feedback and spark effects resulting from extreme tire-to-ground friction. [00:17 - 00:24] [Mid-Air Reconfiguration] — Mechanical Transformation | Action / Physics Directive: The mecha-motorcycle launches off a broken bridge section into the air, with the camera leaping up to track it in a circling shot. While airborne, the motorcycle's shell rapidly flips, deconstructs, and reassembles; the wheels retract into thrusters, and the chassis unfolds to extend steel limbs, instantly transforming from motorcycle mode into a heavy, humanoid combat mecha. Subtext: Showcase the aesthetic of heavy industrial machinery; emphasize the precision interlocking and sense of mass as parts combine, avoiding any "noodle-like" soft-body deformation. [00:25 - 00:30] [Heavy Landing] — A Moment of Power | Action / Physics Directive: The camera rapidly descends to a low-angle, close-up shot looking up at the mecha's face. The humanoid mech drops to one knee, slamming heavily onto the roadway. The impact of its immense tonnage causes the bridge surface to shatter in a spiderweb pattern, while the resulting shockwave instantly clears away the surrounding rain in an expanding ring. The mech slowly lifts its head; a crimson tactical eye-light flares to life, fixing a direct, unblinking stare at the camera. Subtext of the shot: It creates a visually explosive "Superhero Landing," using the shattered pavement and the blast of displaced air to convey the mech's terrifying weight and destructive power to the audience.
- Labelling sections as physics directives makes the model treat spray and exhaust as simulation, not decoration.
- The chase camera position is fixed relative to the vehicle, so speed stays legible across the sequence.
- Rain gives every movement a visible trace, which is what makes the velocity readable.
Olympic Badminton Smash Slow Motion
A single slow-motion smash at an Olympic badminton final, focused on facial intensity and arm muscle at the moment of contact.
A cinematic slow-motion shot of a professional Caucasian male badminton player competing in the Olympic finals. He leaps high into the air with explosive power for a powerful smash. Focus on the intense facial expression and the flexed muscles of his arm. As he hits the shuttlecock, a subtle motion blur and wind effect are visible. The background shows a packed Olympic arena with blurred crowds and bright stadium lights. Smooth camera tracking following his jump. 4K, ultra-realistic, high frame rate, vivid colors, athletic anatomy, professional sports photography style.
- One athletic moment is enough content for a short clip — no structure needed beyond the contact point.
- Naming the specific body details to focus on directs the framing without a shot list.
- A blurred arena crowd provides scale and context while staying cheap to render.
Stylized 3D Family Animation One-Shot
A single flowing 30-second take in modern family-animation style, with oversized heads and clay-like surfaces held throughout.
High-quality 3D animated cartoon, stylized modern family-animation film look, oversized heads, big expressive eyes, exaggerated proportions, smooth rounded clay-like 3D surfaces, subsurface scattering skin, vibrant saturated colors, cinematic animated lighting. NOT realistic, NOT live action. Single continuous 30-second shot, no cuts, one flowing camera move. SUBJECT: a young woman with an oversized round head, huge expressive eyes, dark hair in a messy bun, a long mustard-yellow raincoat, boots, a small satchel. Same design, hair, and outfit throughout, no drift. LOCATION: a cozy stylized night market in the rain, narrow covered lane, strings of warm hanging bulbs, steaming food stalls with rounded cartoon awnings, friendly cartoon vendors and shoppers moving around her, glossy wet cobblestones reflecting the lights, puddles everywhere. COLOR 60:30:10 — 60% deep blue rainy night and wet stone / 30% warm golden bulb and stall light / 10% accent of her mustard-yellow raincoat. 0–8s: the camera tracks backward ahead of her as she walks through the market with a small bounce in her step, dodging puddles, steam curling from stalls, vendors waving as she passes. 8–16s: the camera arcs smoothly around to her side, revealing the full depth of the market behind her, then rises to follow just over her shoulder as she stops to smile at a stall of glowing paper lanterns. 16–24s: she turns down a quieter narrow alley, the camera following, the crowd noise falling away, single bulbs swinging gently overhead, her reflection rippling through a puddle as she steps over it. 24–30s: the camera cranes up and pulls back into a wide as she reaches a warmly lit doorway at the alley's end, pauses, shakes the rain off her coat, and steps inside. Hold on the glowing doorway. PHYSICS: raindrops bounce and splash with cartoon weight, her coat swings and ripples as she walks, puddles ripple outward from each step, steam rises and curls, hanging bulbs sway gently. AUDIO: rain pattering on awnings, cheerful market chatter, sizzling food, her boots splashing, the noise thinning to soft rain in the alley, a warm door chime at the end. FORBIDDEN: no cuts, no design drift in face, hair, or coat, no realistic or live-action rendering, no auto-generated subtitles, no background music, no readable text or logos, no named studio references, no warping geometry.
- NOT realistic, NOT live action in capital letters is a blunt but effective guard against the model drifting photoreal.
- Surface qualities are named specifically — rounded clay-like, subsurface scattering — which pins the render style.
- One continuous camera move suits stylised animation, where cuts would break the flowing feel.
Three-Minute Rain Temple Swordfight
A continuous three-minute grounded swordfight against twenty masked attackers in a rain-soaked abandoned mountain temple.
生成一段完整连续的3分钟写实古装武打电影片段。横屏16:9，2.35:1电影宽银幕构图，24fps，4K电影质感，冷峻低饱和蓝灰色调，真实物理动作，凌厉但克制的写实武侠风格。动作设计强调力量、速度、重心、惯性和空间利用，不使用仙术、轻功飞行或夸张能量特效。 故事发生在暴雨深夜的一座废弃山寺。青石庭院积满雨水，屋檐不断滴水，破损灯笼在风中摇晃，暖黄色火光与冷蓝色月光形成强烈对比。男主约三十岁，黑发高束，穿深靛蓝色窄袖短袍、黑色长裤和旧皮护腕，身形精悍，神情冷静，右手握一把带有磨损痕迹的窄刃长刀。二十余名蒙面敌人穿统一黑色夜行衣，从山门、回廊和屋顶逐渐包围男主，分别使用短刀、长枪、铁棍和锁链。所有人物外形、服装、兵器、伤势和位置前后保持一致，敌人数量随着战斗逐渐减少，不得凭空增加。 0-15秒：暴雨中的山寺全景，镜头穿过密集雨幕缓慢下降，越过残破屋檐和摇晃灯笼，落到青石庭院中央。男主背对镜头独自站立，雨水顺着刀鞘不断滴落。二十余名黑衣敌人从四面回廊、山门和屋顶无声出现，形成层层包围。镜头贴近男主右手，他用拇指缓缓顶开刀镡，刀刃露出一线寒光。敌人首领在回廊阴影中低声说道：“拿下。”男主抬起眼睛，平静回答：“让开。”伴随低沉雷声，第一批敌人突然冲出。 15-30秒：四名持短刀敌人从正面和两侧同时夹击。镜头采用贴身手持跟拍，男主侧身避开第一刀，用刀鞘撞开第二人的手腕，反手拔刀格挡第三人的横斩，金属碰撞迸出短促火星。他不做多余动作，连续使用肩撞、肘击、扫腿和刀背重击，将三名敌人迅速击倒。第四名敌人从背后扑来，男主听到脚步声，低头避开刀锋，转身用刀柄击中对方面部，再借对方身体挡住迎面刺来的长枪。镜头绕男主半圈，其他敌人立刻收紧包围，没有停下来等待。 30-45秒：六名长枪敌人组成半圆枪阵，同时向男主逼近，枪尖不断封锁他的退路。男主没有正面硬拼，而是快速退向庭院狭窄石阶，引诱枪阵收缩。第一排长枪同时刺出时，他踩着湿滑石阶侧身滑下，刀锋由下向上连续斩断两根枪杆，随后抓住断裂枪杆向侧面拨打，令另外三支长枪互相碰撞。他踩上一尊倾斜的石狮，借高度越过低扫的枪杆，落下时以膝撞击倒一名枪手。镜头从低角度跟随落地动作，雨水被双脚猛烈溅开。 45-60秒：屋顶上的敌人突然跃下，前后夹击男主。镜头迅速仰拍，两道黑影穿过灯笼和雨幕落向庭院。男主翻身滚过地面，刀锋贴着敌人的靴底掠过，顺势来到回廊入口。他利用廊柱阻挡多人围攻，让敌人无法同时展开。两名敌人一左一右贴近，男主用刀背压住左侧短刀，抬腿踢中右侧敌人的膝弯，再借廊柱反弹转身，将左侧敌人撞进后方人群。一个灯笼被刀锋割断，从空中落下，在积水中熄灭，画面短暂陷入半明半暗。 60-75秒：战斗进入第一次高潮。剩余敌人分成前后两队，在回廊中高速追击男主。镜头采用侧面长距离跟拍，男主一边后退一边格挡连续刀击，刀锋、雨水和火星在画面中交错。他突然踢翻长凳，迫使前排敌人跳跃躲避，自己从长凳下方滑过，起身后连续击中两人的腰腹和手腕。另一名敌人从柱后偷袭，男主用左手抓住对方持刀手臂，将其带向廊柱，迫使刀锋嵌入木柱，再用肩膀将其撞倒。动作紧凑、真实、清晰，不出现无意义旋转。 75-90秒：山门外的弩手突然射击。弩箭穿过雨幕击碎回廊木窗，男主迅速掀起一张木桌作为盾牌。镜头紧贴木桌另一侧，数支弩箭接连穿透桌面，箭头距离男主面部只有几厘米。男主顶着木桌向前冲撞，将两名敌人压倒在台阶上，随后把木桌推向弩手方向，趁遮挡翻滚进入大殿。敌人紧随其后冲进殿内。最后一支弩箭擦过男主左肩，划破衣袖，留下明显但不过度血腥的伤口。从此刻开始，男主左臂活动受到轻微影响，呼吸逐渐沉重。 90-105秒：大殿内部空间狭窄，残破佛像和木柱形成复杂障碍。一个身材魁梧的敌人挥舞铁棍迎面砸下，男主横刀抵挡，却被巨大力量震退，长刀脱手滑到佛像台阶下。魁梧敌人连续挥棍横扫，男主俯身闪避，铁棍击碎木柱表面。男主贴近对方，让长兵器无法发挥，用掌根、肘击和膝撞连续攻击对方胸腹，然后抓住铁棍中段借力旋转，将魁梧敌人摔过肩膀，砸碎旁边长桌。男主没有时间拾刀，只能夺下一根断裂枪杆作为短棍迎敌。 105-120秒：四名敌人在大殿中同时围攻。男主使用断枪进行近身棍法，挡住两把短刀，利用枪杆两端分别打击敌人的手腕、喉前和膝盖。镜头在木柱之间快速横移，通过柱子遮挡完成自然转场。男主故意露出破绽，引诱两名敌人同时进攻，最后一刻侧身闪开，让二人的兵器互相卡住。他用断枪横扫二人腿部，再踩住掉落的短刀，将短刀踢到手中。另一名敌人从佛像上方扑下，男主举起短刀格挡，巨大的冲击让两人同时摔出殿门，重新落入暴雨庭院。 120-135秒：男主在积水中翻滚起身，敌人首领终于从回廊阴影中走出。首领身材高瘦，使用一把带锁链的弯刃，动作冷静而危险。剩余敌人退到四周封锁出口。首领甩动锁链，弯刃贴着地面划过，激起一道水浪。男主连续后退闪避，弯刃缠住他的短刀并猛然拉走。首领第二次甩出锁链，缠住男主脚踝，将他拖倒在湿滑地面。男主在被拖动过程中抓住一块破碎瓦片，割开缠绕脚踝的布带，翻身避开从上方劈落的弯刃。弯刃重重砸进青石地面，火星和雨水同时炸开。 135-150秒：三名剩余敌人趁男主倒地同时冲来。男主已经疲惫，左肩受伤，动作明显不再轻松。他故意保持半跪姿势，引诱第一人靠近，突然抓住对方手腕，将其带入首领再次甩来的锁链轨迹。锁链缠住敌人的兵器，造成短暂混乱。男主利用湿滑地面低身旋转扫腿，使另外两人失去平衡，再用刀鞘和拳肘连续击倒。最后一名敌人试图从背后刺击，男主在积水倒影中看见对方，头也不回地向后撞肘，随后转身用掌根将其击倒。庭院里只剩男主与首领相对而立。 150-165秒：最终决斗。雷声骤然炸响，首领抽回锁链弯刃，发动连续快速攻击。镜头在广角全景和刀锋特写之间切换：弯刃横扫、锁链回旋、男主侧闪、格挡、翻滚，每一次动作都清晰连贯。男主捡回落在庭院边缘的长刀，用刀身缠住锁链，却被首领猛力拉近。两人在极近距离展开拳肘搏斗，首领击中男主伤肩，男主痛苦后退，长刀再次险些脱手。首领高举弯刃完成最后一击时，画面短暂升格，男主没有后退，而是突然向前贴身进入锁链内圈，用护腕架开首领手臂，以刀柄重击其胸口。 165-180秒：恢复正常速度。首领踉跄后退仍想挥刀，男主踩住落在积水中的锁链，旋身夺下弯刃，再用长刀精准架在首领颈侧，动作突然停止。雨声重新变得清晰，首领手中的兵器缓缓掉落，跪倒在地。男主没有补刀，只是收刀入鞘。镜头缓慢拉远，庭院中敌人全部失去战斗能力，兵器散落在雨水里，没有血腥特写。男主扶着受伤的左肩穿过山门，破晓的微光从远处云层后出现。最后一个镜头停留在积水中的刀痕和逐渐平静的波纹上，远处传来男主渐行渐远的脚步声，画面自然淡出。 镜头要求：整段战斗保持明确的空间方向和人物位置，使用大远景交代战场，中近景呈现攻防动作，适量使用贴身手持跟拍、低角度跟拍、环绕移动、遮挡转场和关键动作升格；不要频繁无意义快切，不要让镜头晃动到看不清动作。敌人必须采取包围、夹击、枪阵、远程掩护和多人协同，不能排队等待男主逐个攻击。男主通过地形、廊柱、石阶、长凳、木桌和敌人之间的位置关系化解人数劣势。 声音设计：全程保留真实暴雨声、雷声、急促脚步声、衣料摩擦声、呼吸声、刀剑碰撞声、木材碎裂声和兵器落地声。配乐以前半段低沉鼓点和弦乐持续积累，中段加入快速鼓点，最终决斗时音乐达到高潮；首领跪倒后音乐立刻停止，只保留雨声和脚步声。 禁止出现：仙术、飞行、能量波、武器发光、夸张爆炸、血腥肢解、现代物品、字幕、文字、LOGO和水印；禁止人物脸部突变、服装变化、额外肢体、兵器凭空出现或消失、敌人数量突然增加、同一个敌人重复出现、动作穿模、无重力漂浮、连续无意义空翻以及男主毫发无伤。整段必须像一场真正拍摄完成、叙事清楚、动作连贯、逐步升级的3分钟电影级武打戏。
- Banning flight and energy effects keeps the choreography in believable physical wuxia.
- Enemy count is required to only decrease, which prevents the model from spawning fresh attackers.
- Warm lantern light against cold moonlight gives three minutes of fighting a consistent visual scheme.
More styles & techniques
Cinematic stories, VFX and editing workflows, music and dance — the rest of the library.
Cinematic Steampunk Motion Graphics
A 30-second seamless 3D motion-graphics journey through a steampunk miniature world, gliding from brass gears to a clockwork ship and a glowing moon.
A high-end, intensely cinematic 30-second 3D motion-graphics sequence in a refined steampunk and vintage-miniature style, with continuous, fluid orbiting and tunneling camera moves. [0-10s]: A macro close-up of an antique brass clock face that miraculously unfolds layer by layer into interlocking rotating gear rings and volumetric fog. The camera dives down through the gears, where an Ornithopter is spiraling up out of a miniature canyon built from stacked, weathered antique books. [10-20s]: The camera follows the ornithopter's trajectory as it glides forward, seamlessly passing into an ornate, fast-spinning brass Zoetrope whose interior projects the dynamic light and shadow of galloping mechanical horses. The light leaps out of the box and the scene instantly becomes a brass-textured floating cable car, threading along faintly glowing copper rails through a forest of mechanical gears, bathed in cinematic golden-hour light. [20-30s]: The camera pans gracefully downward and a delicate clockwork wooden sailing ship appears beneath the cable car, cutting through rolling waves of deep-blue glass material. The end of the waves seamlessly evolves into a glowing giant moon, where a group of silhouetted explorers holding swaying lanterns trudge along a crystal-vein ridge under a starry sky. The camera spirals smoothly outward, passing through ethereal clouds, back to the grand, ticking brass clock face. Technical specs: hyper-real mechanical textures, rich brass and gold tones, cinematic shallow depth of field. Smooth, continuous, seamless tunneling camera moves, with a powerful epic and fantastical adventure atmosphere.
- Each 10-second beat morphs one mechanical object into the next, so the whole 30 seconds reads as a single uninterrupted shot.
- A consistent brass-and-gold palette with cinematic shallow depth of field ties every scene into one coherent steampunk world.
- Volumetric light and hyper-real material textures give the miniature scale a believable, epic sense of weight.
Official showcaseSeamless 3D journeyMotion graphics
Electric Witch Transformation Sequence
A 30-second magical transformation in a storm-black void, where each lightning strike advances the character's hair, costume and power one stage further.
30-second cinematic magical transformation sequence, multiple logically connected shots, consistent character identity and seamless visual progression. 0–3s: Extreme wide shot in a storm-black infinite void. An electric witch floats upright, initially wearing a simple dark silhouette. Frozen white-blue lightning bolts surround her like cracks suspended in space. Slow dolly-in as electrical pressure vibrates through the darkness. 3–7s: The first lightning strike crosses behind her. Snap-zoom into a close-up as her dark hair flashes into saturated violet with brilliant cyan ends. Individual strands rise and ripple in the electrical field; intense white-blue rim light outlines her face. 7–11s: A second strike fractures the air across her torso. Whip-pan downward as sharp layered robes assemble from glowing electric fissures, angular fabric panels locking around her body with realistic weight and dramatic cloth movement. 11–15s: Macro close-ups of both hands and collarbone. Crescent-shaped markings ignite and race across her skin in precise cyan-white trails, pulsing brighter with every sharp thunder transient. 15–20s: Wide low-angle hero shot. She raises one empty hand. A descending thunderbolt compresses into her palm, twists, and hardens into a crooked lightning wand. Orbit camera around her as branching electricity coils around the newly formed wand. 20–24s: Camera snap-zooms beneath her feet. A circular storm-rune sigil burns open below her, concentric symbols rotating in opposite directions while white-blue arcs connect the rune, her robes, markings, hair, and wand. 24–28s: Rapid rhythmic montage: extreme close-up of glowing eyes, cyan hair tips, crescent markings, layered robe edges, gripping fingers, and the wand tip gathering a dense sphere of electricity. Alternate macro details with wide heroic angles; each lightning impact motivates the cut. 28–30s: Low-angle crane-back as she swings the wand forward and locks into a signature spell-casting pose. A vast electric starburst erupts behind her, frozen lightning radiating symmetrically around her silhouette. Hold the final iconic frame. Stock-footage grandeur played completely sincere, premium fantasy-commercial finish, deep blacks, brilliant cyan-white highlights, realistic electrical illumination, monumental scale.
- Every beat is pinned to a timecode, so the transformation escalates on a schedule instead of drifting.
- One consistent light source — the lightning — motivates every change, which keeps 30 seconds of VFX visually coherent.
- Describing individual hair strands and rim light gives the model concrete detail to hold identity through the change.
30s transformationBeat-timed lightningVFX sequence
Dance Transition Scene Swap
One dance is replicated from a reference video while the performer and scene swap at each transition point.
【基础设定】一段女生不同场景跳“”拖拉机舞“”，并在中途完成丝滑转场的视频，真人写实质感。人物跳舞动作，位置关系严格参考 {{Mixed 3}} 复刻动作轨迹 ； 0-3秒：将参考视频里面的主体替换成女生d72f88ea-9673-461d-9f75-87a4040f02e0，场景跟随变化；女生没有尾巴，首帧画面就是女主拿着短刀，高高举起手，跟参考视频的首帧动作完全一致 3-6秒：女生通过一个舞蹈工作衔接特效转场变成exec-9219a05b-ee6d-4c5b-9176-edad734b296d ，场景跟随变化；女生继续参考视频的动作完成舞蹈 6-9秒：女生通过一个舞蹈工作衔接特效转场变成exec-a1caf641-08fc-4f8d-b156-c084277123be，场景跟随变化；女生继续参考视频的动作完成舞蹈 9-15秒：女生通过一个舞蹈工作衔接特效转场变成image，场景跟随变化；女生继续参考视频的动作完成舞蹈 【限制】动作不漂移，不跳帧，不改变人物的数量和站位；全程画面只有一个女生在跳舞，不要肢体融合、重复肢体或主体消失。轮廓稳定。仅生成音效，不要生成背景音乐。女生全程没有尾巴
- Requiring the first frame to match the reference exactly guarantees the motion transfer starts cleanly.
- Transitions are placed on dance moves, so the swaps hide inside the choreography.
- The scene changes with each character swap, keeping the loop visually fresh.
Dance from a reference videoScene swap per transitionEditing workflow
Y2K Pop Duo Music Video
A retro Y2K music video with candy-colored sets, synchronised hand choreography and beat-locked hard cuts at modern production quality.
**[SCENE]** A two-member female pop duo shoots a retro Y2K-style music video: candy-colored studio sets, tightly synchronized hand choreography, beat-locked hard cuts and fast punch zooms — the texture of 1999 music television, rendered at modern production quality. **[ACTIVE REFERENCES]** <<<image_1>>>: Female singer in her twenties, long straight pink hair with gold hair clips, small nose ring, beauty mark on cheek, white printed crop top, silver chain necklace, chain belt, light-blue washed baggy jeans, off-white platform sneakers. Playful and confident. 100% match to reference image. <<<image_2>>>: Female singer in her twenties, long straight black hair with silver hair clips, light blue eyes with silver glitter eyeshadow, red cord necklace with ruby pendant, gray raglan short-sleeve tee with a gray jacket draped over the shoulders, dark gray pleated skirt with bow, gray knee socks, black platform shoes. Cool and commanding. 100% match to reference image. **[SET MAP]** Three practical studio sets, each roughly 4 meters deep, facing camera: Set A — bubblegum-pink seamless cyclorama, glossy reflective floor, two rows of round studio light bulbs on the back wall. Set B — cobalt-blue seamless cyclorama, a single hard white spotlight circle on the floor. Set C — floor-to-ceiling silver rain-strand curtain wall, mirrored floor. **[FIRST FRAME & SPATIAL LAYOUT]** The first visible frame already contains both girls, on Set A: <<<image_1>>> at frame-left x40%, <<<image_2>>> at right x60%, medium-shot depth, 0.5 m apart, bodies squared to camera, eyes locked on lens, frozen in a mirrored opening pose — inner hand on hip, outer arm raised. No empty establishing shot, no delayed entrance. **[FORMAT]** Controlled multi-shot sequence, seven segments across 15 seconds, every hard cut landing precisely on a musical downbeat. Real-time motion. **[LENS NOTES]** Fisheye = true fisheye wide-angle, 1.5 m from subject, visible barrel distortion at frame edges, deliberate 1999 MV lens language; 47° = standard view, natural proportions; 29° = medium-tele portrait, background lightly compressed; 18° = long-lens close-up, melted bokeh. Locked within each segment, no drift. **[ACTION TIMELINE]** 0.0–2.0s Set A, fisheye low angle: both hit the frozen mirrored pose on beat one, then bounce-groove in sync with every beat, camera slowly pushes in 10%. Hard cut at 2.0s. 2.0–4.0s Set B, 29°: <<<image_2>>> solo dance inside the spotlight circle at x50%, pointed-at-camera precision hand choreography, one fast punch zoom landing exactly on the downbeat. Hard cut at 4.0s. 4.0–6.0s Set C, 47°: <<<image_1>>> whips her pink hair through a full arc, then strides toward camera as the camera pulls back at matched speed, rain-strand curtain shimmering, chain belt swinging. Hard cut at 6.0s. 6.0–8.0s Set B, 18° two-shot close-up: both faces cheek-to-cheek filling the frame, <<<image_1>>> left / <<<image_2>>> right, soft wind lifting pink and black strands, glossy makeup, confident smiles, heads tilting toward each other in sync with the beat. Hard cut at 8.0s. 8.0–11.0s Set A, 47° full body: the chorus dance core — three counts of fully synchronized choreography: wave arms, fast spin, full-body groove into a sharp freeze; positions cross and return, <<<image_1>>> left / <<<image_2>>> right re-locked. Hard cut at 11.0s. 11.0–13.0s Set C, 47°: the two walk toward camera side by side with synchronized arm swings, black and pink hair swinging with each step, reflections in the mirrored floor. Hard cut at 13.0s. 13.0–15.0s Set A, 47°: back-to-back frozen final pose, camera zooms out fast to full body, landing exactly on the last downbeat, one bright camera-flash white sweep over the final frame. **[PHYSICS]** Choreography carries real weight: heel strikes, weight shifts, shoulder isolations with follow-through. Hair whips show visible lag and settle naturally. Chain belt and necklaces swing on the beat points. Rain-strand curtain ripples from body movement. Glossy floor returns soft, believable reflections. **[LIGHTING]** High-key, even studio lighting on every set: large soft frontal key, bright clean exposure, high skin sheen; Set A's bulb rows create back rim light and soft bloom into the lens; Set B's spotlight casts a crisp circular pool; Set C sparkles with hundreds of rain-strand specular highlights. Bright, candy-like, camera-ready — a deliberate flat 1999 broadcast-TV look. **[AUDIO]** Original Y2K bubblegum dance-pop instrumental, 120 BPM, four-on-the-floor kick, bright syncopated synths, faint tape hiss underneath. Every hard cut lands exactly on a downbeat. Instrumental only throughout, no vocals; both girls perform with closed lips, delivering energy purely through expression and choreography. **[POSITIVE LOCKS]** Both faces and identities 100% locked to reference images across all segments including close-ups. Wardrobe stays exactly as referenced across all three sets. Only these two girls appear in the entire video. In every two-person segment <<<image_1>>> is fixed frame-left, <<<image_2>>> fixed frame-right. Within each segment, set geography, spacing, and screen direction stay consistent. **[STYLE]** Shot at modern production quality but graded to 1999 broadcast texture: broadcast-grade videotape master grain layered over high-detail imagery — soft highlight bloom, slight chroma bleed on hard color edges, fine analog tape grain, faint interlace flicker on fast motion; a high-saturation candy palette of bubblegum pink, electric cobalt and chrome silver; Y2K music-television punch-zoom editing energy, with contemporary sharpness preserved underneath.
- Anchoring to a specific year of music television gives the model a precise visual grammar to imitate.
- Hand choreography is called out separately, which is what makes a two-person performance feel tight.
- Beat-locked cuts and punch zooms are named as the edit vocabulary, so the rhythm is authored.
Y2K candy setsBeat-locked hard cutsSynchronised choreography
Multilingual Kinetic Typography
A seamless 15-second loop spelling "create" across eleven languages, each in its own material world with morphing dissolve transitions.
A 15-second seamless looping creative text-animation video, 4K, 30fps. Each language lasts about 1.2s; transitions are achieved through text dissolving, morphing, or particle scattering, with no hard cuts. The background music has a clear rhythm with strong beat-sync. 0-1.2s Chinese "创造" - Op-art optical-illusion pure-black background, black-and-white concentric circles radiating outward from the center into a visual tunnel. White 3D Chinese characters "创造" slowly protrude from deep within the center toward the lens, bold sans-serif with subtle edge shadows. The concentric circles ripple and distort as the text advances, like ripples on water. After fully protruding, the text pauses, then dissolves into scattering blue crayon particles. 1.2-2.4s English "CREATE" - Hand-drawn crayon on warm-yellow kraft-paper texture; rough blue crayon strokes write out the uppercase "CREATE" stroke by stroke. The strokes carry obvious crayon grain and overlap marks, the final crossbar of the E tilting slightly upward. Once finished, the letters have a faint waxy sheen and faint pencil guidelines appear in the background. The text is then sucked into CRT scanlines and vanishes. 2.4-3.6s Spanish "CREAR" - A retro arcade cabinet in a dark frame, the central CRT screen carrying fine scanlines and phosphor grain. Blue-purple gradient 3D pixel letters "CREAR" rise from the bottom, the letter surfaces animated with wave-like white ripples and edges glowing neon blue. "CREDIT 00" sits top-left and "INSERT COIN" blinks bottom-right. The text then pixelates and crumbles into indigo batik patterns. 3.6-4.8s Indonesian "CIPTAKAN" - Batik fabric, deep-indigo traditional Indonesian batik background with fine parabolic patterns. White serif "CIPTAKAN" slowly rises from beneath the fabric like gold foil embossing, the fabric rippling realistically as the text emerges. After it appears, wind lifts the fabric and golden flecks scatter, turning into Islamic geometric patterns. 4.8-6.0s Malay "CIPTA" - Islamic geometry. Deep-green velvet background, golden arabesque geometric patterns spreading from the four corners toward the center. White classical serif "CIPTA" rotates into view from the center, the letters ringed by star patterns with gold-dust particles drifting down. The text is then engraved letter by letter into a black metal plaque by a golden carving blade. 6.0-7.2s Thai "สร้างสรรค์" - Gold-leaf engraving on a black background, the Thai "สร้างสรรค์" rendered in gold as if carved from an ancient temple plaque. The text surface has a subtle gold-leaf flaking animation revealing dark-red primer beneath, with golden flecks scattering. Once carved, the text melts into dripping silver mercury. 7.2-8.4s Arabic "إبداع" - Mechanical flip-board. A black metal split-flap display fills the whole frame, mechanical flaps clacking and flipping in sequence. White pixel-grid Arabic "إبداع" appears letter by letter from right to left, each letter's flip accompanied by precise mechanical motion and slight vibration. Once the flipping is done, the text is swept up by a storm of colorful samba feathers. 8.4-9.6s Portuguese "CRIAR" - Carnival feathers. Black background, colorful samba feathers converging from the frame edges toward the center to form a giant feather fan. White bold "CRIAR" bursts out from the center of the fan, the feathers flying outward with the text's impact, the text surface carrying Carnival glitter reflections and green-yellow-blue Brazilian-flag light spots flickering. The text is then washed away by black ink. 9.6-10.8s Vietnamese "SÁNG TẠO" - Ink on silk. Off-white silk background, black ink slowly flowing from the top of the frame, gradually forming the Vietnamese "SÁNG TẠO". The ink produces natural bleeding edges on the silk, some droplets dripping down into hanging ink beads. Once finished, wind lifts the silk to reveal a lotus pattern beneath, and the text crystallizes into a transparent glass ball. 10.8-12.0s Japanese "創造" - Optical glass. A perfect transparent optical glass ball floats at the center of a pure-black background, refracting rainbow dispersion light spots. Behind the glass ball, the Japanese kanji "創造" appears as rainbow dispersion projection, rotating slowly with the ball, the text undergoing twisting, stretching, and separating optical distortion. The glass ball's surface has fine dust particles, then the ball melts into silver liquid metal. 12.0-13.2s Korean "창조" - Liquid metal. A deep starry-sky background, silver liquid mercury dripping from the top of frame, naturally coalescing in mid-air into the Korean "창조". The liquid text surface has strong mirror reflection, mirroring the surrounding stars. After the text forms, some mercury keeps dripping down into hanging metal beads, until all the liquid metal converges into one giant silver sphere.
- Each language gets a distinct material world, turning a single word into twelve mini set-pieces.
- Every transition is a physical transformation (dissolve, melt, pixelate) so the loop feels continuous rather than cut.
- Tight 1.2-second beats locked to the music keep the kinetic typography energetic and rhythmic.
Coral Reef Glowing Jellyfish
A serene blue coral-reef scene where glowing lavender jellyfish drift in and rising bubbles spell out the seedance logo.
A deep-sea coral-reef scene, a blue-toned tropical underwater world with large expanses of healthy, thriving colorful living coral, including branching coral, brain coral, plate coral, and soft sea-fan coral, with large schools of tropical fish weaving naturally among them. The foreground is crisp and vivid; the distance gradually turns bluer and grayer with reduced contrast. Natural light from above is filtered through the seawater into soft volumetric light, with fine suspended particles and a gentle sense of flow in the water, the soft corals swaying lightly and the fish schools moving smoothly and in coordination. Add a group of semi-transparent pale-lavender glowing jellyfish slowly appearing, 8-12 of them, in varying sizes. Their bell bodies carry a soft bioluminescent effect, tentacles drifting gently with the current, the tentacle tips bearing faint purple light points. The jellyfish are proportioned harmoniously with the corals and fish, the glow soft and not harsh, forming dreamy light spots against the dark seawater background. The jellyfish swarm's movement path is natural, rising in a slow ascending spiral, with some jellyfish swimming past in front of the lens to produce a slight lens-flare effect. Maintain the underwater blue-toned lighting, the jellyfish glow coexisting harmoniously with the faint reflections of the surrounding coral. As the jellyfish swarm swims, they produce bubbles that rise and form the word "Seedance" in the sea.
- Strong atmospheric perspective (crisp foreground, hazy blue distance) gives the underwater scene real depth.
- Soft bioluminescence and a controlled glow keep the jellyfish dreamy without blowing out the dark water.
- The bubble-formed logo turns a natural element into an organic, on-brand reveal.
Peking Opera Heritage Film
A warm, restrained cinematic short on Peking Opera craft, as an old master quietly hands a tradition down to a young apprentice.
A Peking Opera intangible-heritage short, cinematic, oriental aesthetics, warm and restrained. In a traditional troupe's backstage and handcraft workshop, an old master quietly makes Peking Opera headdresses, arranges costumes, and outlines a painted face, the hand details delicate, the silk threads, beadwork, pigments, and embroidery all richly textured. A young apprentice watches attentively beside him, then carefully takes up the tools and completes the small steps under the master's guidance. The master straightens the apprentice's headpiece and adjusts his lapels, as if gently handing over a craft and an emotion into his hands. Finally the young man, fully dressed, stands at the edge of the stage about to go on, faint light illuminating the costume and his profile, the old master quietly watching from behind. The overall mood is quiet, heartfelt, and full of a sense of inheritance, with few subtitles and a few fitting lines of dialogue interspersed.
- Tight hand-detail close-ups make the craftsmanship and material textures the emotional core.
- The master-to-apprentice arc carries a clear theme of inheritance without needing narration.
- Restrained, warm lighting keeps the heritage tone dignified rather than sentimental.
Oceanic Civilization Epic
A 30-second epic sci-fi worldbuild diving into a sunken civilization and rising into space, in the spirit of Dune and Interstellar.
"Oceanic Civilization" (Epic sci-fi / Dune x Interstellar / no real people / sculptural lifeforms) [0-5s | Cosmic-scale opening - the ocean as planetary memory] A deep-blue ocean fills the full frame, the extremely deep water layered like a liquid universe inside a planet. The camera descends slowly and vertically from high altitude, passing through cloud layers and sea mist, into the surface. The sea surface ripples like a metallic film, refracting irregular cracks of sunlight, with intensely epic volumetric light. [5-10s | Entering the deep-sea civilization fault] The camera pierces the surface and enters the deep sea. A vast "undersea civilization structure" gradually appears: fractured ring-shaped megastructures, a sunken stone dome, floating geometric ruin platforms. The structural style fuses ancient temples with alien-civilization technology (like the Dune ruin language). Faintly glowing particles drift suspended in the water, like stardust slowly drifting through the sea. [10-15s | A sculptural lifeform appears (non-human)] At the center of the theater stands a giant sculptural lifeform: a "humanoid idol" made of white stone and semi-transparent minerals, but with no living detail (no skin, no real human features). Its posture is like an ancient ritual structure, the body in segmented geometric forms, like a civilization's memory vessel. The sculpture's surface is long-eroded by water currents, covered in algae and crystallized coral structures. The camera slowly orbits the sculpture, creating a "deity descending" feeling. [15-20s | The civilization awakens - light flow activates] The entire undersea ruin begins to "wake". Faint energy-flow light patterns appear inside the sculpture, lighting up like a neural network. Fractured stone pillars slowly rise and reassemble into a ring-shaped theater structure. The water begins to flow with "order", as if space is being recomputed. The camera moves from static orbit to a slight accelerating spin. [20-24s | The sea surface reverses - rising breakthrough] The camera suddenly accelerates upward and bursts out of the sea. The seawater separates to both sides as if torn open, forming a giant water curtain. A giant ancient-civilization ship/temple hull rises from the seabed: its form a hybrid of stone temple and sci-fi vessel, the surface covered in coral and mineralized structures. The hull rises with seawater cascading off it like waterfalls. [24-27s | Epic rotating shot (visual climax)] The camera spirals upward at high speed around the giant ship (spiral orbit shot). The sun pierces through a crack in the clouds, forming a sacred light column. The water currents are stretched into spiral forms by the rotation, like a galactic structure. The hull slowly rotates, revealing its enormous structure: more like a "mobile civilization ruin" than a vehicle. [27-30s | Ultimate wide shot - the scale of civilization revealed] The camera pulls back at extreme speed to a space-level view. The ocean, the ruins, the rising giant ship, and the sculptural temple are arranged vertically in the same frame: forming a three-tier cosmic structure of "undersea civilization - sea surface - sky light layer". The whole world is like an awakened ancient-planet memory system. The final image slowly closes into a black screen, leaving only faint light points. Epic sci-fi aesthetic / Dune-style sand-sea civilization structure / Interstellar-scale spatial dimension / no-character narrative / sculptural civilization ruins / alien temple structures / volumetric light penetrating seawater / megastructure collapse and reassembly / sacred ritual camera language / spiral camera moves / stardust-particle ocean / high-dynamic-range cinematic realism.
- A vertical descend-then-ascend journey gives a no-character film a strong, legible structure.
- Named references (Dune, Interstellar) anchor the scale and material language precisely.
- The final space-level wide shot reveals the full three-tier world, paying off the scale promise.
Energy Bow VFX Edit
A controllable edit that adds a glowing blue-white energy bow and arrow into an existing jungle clip while preserving its motion.
Keep the character, jungle environment, camera movement, composition, action rhythm, and duration in [reference video 1] unchanged. A blue-white energy bow and a glowing arrow [reference image 1] slowly appear in the character's hand, the bow gradually coalescing into form from faint electric arcs and particles, carrying a delicate flowing electric-current texture, slight volumetric light, and a stable energy contour. During the draw, the arrow condenses into a bright energy arrow at the center of the bowstring; the instant the character releases, the arrow shoots out at high speed, leaving a bright, slender, continuous, razor-sharp energy trail.
- Explicitly locking the source clip preserves the original performance while adding the effect.
- A reference image defines the energy weapon so the VFX matches the intended look.
- Describing the bow forming from arcs and particles gives the addition believable motion.
Drone Object Removal Edit
A clean object-removal edit that deletes a drone and foreground track from a giraffe clip and naturally fills the gap.
Delete the drone and the foreground track / vehicle-body edge in the lower-left of the [reference video 1] frame, and naturally fill in the deleted areas. Keep the giraffe herd, tree branches, distant savanna, golden backlit sunset, aerial perspective, and shot composition completely unchanged. The filled-in background should be consistent with the surrounding environment, generating natural sky, gaps between branches, and grass detail, with no smearing, flickering, deformation, ghosting, or jitter. Ensure the frame-to-frame temporal consistency and continuous motion of the video before and after, with natural edge transitions, the whole looking like the original live-action footage.
- Naming exactly what to remove and what to preserve keeps the cleanup surgical.
- Calling out artifacts to avoid (smearing, flicker, ghosting) steers toward a clean inpaint.
- Emphasizing temporal consistency keeps the fill stable across frames.
Martial Arts Restyle Edit
A restyle edit that turns a plain sparring clip into a classical pre-duel stand-off, swapping the setting and both fighters wardrobe.
Replace the plain two-person martial-arts sparring video [reference video 1] with a bare-handed feeling-out style before a cold-weapon duel. Replace the scene with a medieval stone-castle platform, an ancient courtyard ground, a mountain-fortress outer platform, or a simple stone-brick dueling ground, the background being castle walls, wind, fog, a distant mountain line, the ground flat stone [reference image 1]. Replace the wardrobe of the man in dark clothing in the video with [reference image 2], and replace the man in light clothing in the video with [reference image 3]. The actions still stay unchanged, not altering the original rhythm. The AI effects only enhance the environment and texture: wind blowing the garment hems, light fog, a small amount of dust at contact points, a cold-toned metallic reflective quality, slight grain, and epic color grading. The overall style is restrained, realistic, classical hard-edged duel atmosphere. The background music is beat-synced.
- Preserving the original choreography while swapping setting and wardrobe is an efficient restyle.
- Reference images for environment and both fighters keep the new look precise and consistent.
- Limiting AI effects to environment and texture avoids disturbing the believable action.
Victorian Greenhouse and Mechanical Hummingbird
A 15-second storm sequence with a consistent explorer, a mechanical hummingbird, physical contact, Spanish dialogue, and a final bioluminescent reveal.
15-second photorealistic cinematic video, 16:9, with synchronized stereo audio. A female explorer with short black hair, a red waterproof jacket, and a gray backpack remains perfectly consistent inside an abandoned Victorian greenhouse during a nighttime storm. 0–4s: A low-angle tracking shot follows her walking across the wet floor. Her boot hits a puddle, creating a physically accurate splash. 4–8s: Without a cut, the camera moves into a medium side-tracking shot. She pushes aside a wet branch as a brass mechanical hummingbird emerges, circles her head, and casts warm golden light across her face. 8–12s: The camera performs a fluid 120-degree orbit. She extends her hand and the hummingbird lands precisely on her finger. Its wings slow naturally as water droplets fall from its metallic body. She says in Spanish, with natural lip sync: “Así que eras real.” 12–15s: Lightning illuminates the greenhouse. A rapid rack focus reveals an enormous bioluminescent flower opening in the background and releasing glowing blue particles. The explorer and hummingbird turn toward it simultaneously. End with a slow push toward the flower. 35mm anamorphic cinematography, natural depth of field, realistic physics, coherent reflections, detailed skin, blue storm light contrasted with the hummingbird’s golden glow. Immersive stereo rain, wind, vibrating glass, synchronized footsteps and splashes, spatial mechanical buzzing, clean dialogue, and one deep musical note when the flower opens. Priorities: absolute character and wardrobe consistency, stable hummingbird design, correct anatomy, natural hands, precise physical contact, coherent movement, consistent lighting, and continuous camera motion. Exactly one explorer and one hummingbird. No subtitles, text, logos, or additional characters.
- Four timestamped beats coordinate camera motion, physical interaction, dialogue, and the final reveal.
- The prompt repeats consistency rules for both the explorer and the mechanical hummingbird.
- Separate audio layers make the storm, footsteps, mechanical buzz, dialogue, and music easier to prioritize.
Late-1990s Paint Program Illusion
A live-action illusion staged inside a faithfully rebuilt 1990s desktop paint program, where a man climbs out of the painted landscape.
Create a ten second cinematic live action illusion in a sixteen by nine frame at thirty frames per second. Begin inside a faithfully recreated late nineteen nineties desktop paint program. Use a cool gray window frame, navy title bar, simple menus, chunky pixel tool icons on the left, scroll bars, and small color swatches along the bottom. The canvas shows a saturated blue sky with soft white clouds and a vivid green grassy hill, nostalgic but photographed with realistic depth, subtle cloud movement, and light atmospheric haze. 0 to 1.2 seconds. Hold a locked frontal camera on the full paint window. The empty landscape fills the canvas. A slim young adult man rises smoothly from the bottom center with his back to camera. He wears a red athletic shirt with white collar and sleeve stripes, a backward royal blue cap, a thin silver chain, and black ink forearm tattoos. Give his movement real body weight, natural shoulder motion, and slight cloth drag. 1.2 to 2.5 seconds. He lifts his tattooed right arm toward the upper left of the canvas as though touching an invisible drawing tool. Keep the interface perfectly stable and sharp. He turns clockwise toward camera, lowers his hand, and settles into a relaxed waist up pose at center. Use soft frontal daylight, a gentle key from camera left, believable skin texture, clear eyes, fine facial hair, and a faint contact shadow. 2.5 to 6.2 seconds. He looks into camera with a playful calm expression, raises one index finger, and draws in midair. A warm ivory line appears exactly at the fingertip and follows every gesture without delay. It looks like a real textured paint stroke with slight thickness variation, dry brush edges, and a soft glow. He draws one continuous five point star around his body. Make the tall upper point above his cap, the right point beside his shoulder, the lower left point across his torso, the lower right point, then close the shape near his raised hand. Preserve correct hand anatomy, stable identity, perfect line continuity, and natural reactions from his free hand. 6.2 to 7.4 seconds. When the star closes, perform a smooth optical push into the canvas until the interface edges slide beyond the frame. The move should feel like a real camera passing through a monitor, with subtle lens breathing and no cut. He smiles softly and lifts both palms in a small satisfied reveal while the completed ivory star floats around him. 7.4 to 10 seconds. He glances right and walks naturally out of frame. Keep the camera locked on the empty hill and sky. The star remains suspended, slowly loses brightness, and becomes slightly transparent without vanishing. End with one cloud drifting through its center. Maintain one continuous shot, realistic motion blur, natural blinking, stable clothing and tattoos, accurate perspective, clean edges, no warped limbs, no duplicate fingers, no facial changes, no flicker, no random objects, no extra people, and no artificial plastic skin. Make it feel like a practical live action performance composited into an authentic retro computer interface. Audio. Add an original playful retro electronic instrumental at about one hundred and five beats per minute with a warm drum machine groove, soft bass, bright synth plucks, and subtle digital ambience. Sync a light mouse click to the first hand gesture, delicate paint stroke swishes to the fingertip, a sparkling chime when the star closes, and a soft whoosh during the push into the canvas. No vocals and no dialogue.
- The UI is described element by element — title bar, tool icons, scroll bars — so the fake desktop reads as period-accurate.
- Holding a locked frontal camera makes the illusion legible; any camera move would break the flat-screen conceit.
- The canvas is asked to behave photographically (depth, haze, cloud drift) while still looking painted, which is what sells the crossover.
Photoreal Slice-of-Life Portrait Film
A vertical slice-of-life film specified down to lens choice, skin pores and lens artefacts so the result reads as real footage rather than render.
Prompt: Create a 30-second ultra-photorealistic cinematic slice-of-life film that is visually indistinguishable from real footage. Every frame should resemble a premium Netflix lifestyle documentary or luxury commercial, captured on a professional full-frame cinema camera using 50mm and 85mm prime lenses in true 8K HDR. Use physically accurate lighting, natural dynamic range, realistic optical lens characteristics, shallow depth of field, subtle film grain, authentic motion blur, lifelike skin with visible pores, realistic eye reflections, accurate fabric simulation, and natural environmental details. Avoid any CGI or AI-generated appearance. The film follows a 30-year-old European woman living a peaceful countryside life. She has naturally tied brown hair with loose flyaway strands, minimal makeup, expressive eyes, realistic skin texture, and wears comfortable linen clothing in warm neutral tones. Every movement should feel subconscious and naturally observed—never posed or performed. She never looks directly into the camera, and her expressions remain subtle and genuine. The story begins inside a cozy farmhouse at sunrise as warm morning light fills the bedroom. She wakes naturally, opens the wooden window, and breathes in the fresh countryside air while looking across mist-covered fields. She then prepares fresh bread in a rustic kitchen, kneading dough by hand, placing it into a traditional oven, and cleaning the wooden countertop with calm, deliberate movements. Next, she walks into her small garden, gently watering herbs, collecting ripe tomatoes, and brushing her fingers across fresh plants while sunlight creates soft natural lens flares. Afterwards, she pours fresh coffee into a handmade ceramic mug and quietly reads a book beside a large window as sunlight illuminates floating dust particles. The journey continues with a relaxed walk through a charming European village lined with stone cottages, flower-filled windows, bicycles, and narrow streets before she visits a small local market to purchase fresh flowers and seasonal fruit. The film ends during golden hour as she returns home, arranges the flowers in a glass vase, sits peacefully by the window overlooking the countryside, and the camera slowly pulls away before fading naturally to black. Performance Direction: Every action should feel authentic and unplanned. Include natural blinking, relaxed breathing, realistic eye movement, subtle posture adjustments, correct body weight shifts, accurate finger anatomy, believable hand interaction with objects, natural walking speed, realistic hair movement, and true-to-life fabric physics. Nothing should resemble acting or posing. Audio Design (Critical): No dialogue, no narration, no subtitles, and absolutely no background music. Tell the story entirely through immersive environmental ASMR. Synchronize every sound naturally with the visuals, including birds singing, gentle wind, wooden floor creaks, curtain movement, dough kneading, ceramic bowls, oven door, running water, leaves rustling, footsteps on grass and stone paths, distant village ambience, market sounds, paper bags, coffee pouring, spoon stirring, page turns, doors opening, evening insects, and quiet countryside room tone. Creative Goal: Deliver a calm, intimate, emotionally grounded slice-of-life film that feels as though it was captured by a real documentary filmmaker. The final result should be so realistic, natural, and immersive that viewers genuinely question whether it was filmed with a real camera rather than generated by AI.
- Realism is requested as a checklist of physical properties — dynamic range, motion blur, fabric behaviour — not as the word photorealistic.
- Naming 50mm and 85mm primes constrains the framing to what those focal lengths can actually do.
- Explicitly banning a CGI look gives the model a negative target alongside the positive ones.
Doorway Peephole Fisheye POV
A fixed peephole POV of an apartment hallway, where a visitor keeps returning to the lens in different outfits and moods.
A realistic doorway peephole POV video shot through a ultra wide fisheye lens with a pronounced circular black vignette and curved distortion. The scene takes place in a warmly lit, carpeted apartment hallway with dark doors and warm sconce lights running along the walls. A cheerful young woman with short, bleached blonde pixie cut hair, wearing a casual layered outfit, approaches the camera close up, leaning in and playfully knocking on the lens as if knocking on a door. She holds a large fresh bouquet of white daisies and eucalyptus. She smiles brightly, applies lip balm while looking into the camera, spins around happily, and runs off down the corridor. Next, she returns wearing an oversized cream-colored trench coat carrying a small red gift bag, knocks again, poses, turns, and playfully darts away down the hallway before running back toward the door. Finally, she returns wearing a warm brown sweater, holding a frosted red velvet cake on a glass plate. She knocks on the camera lens, licks frosting off her finger, smiles, blows a kiss directly to the camera lens, and runs off giggling. Natural handheld instability, realistic indoor lighting, handheld camera movement, high definition organic video quality, upbeat indie pop background soundtrack. Aspect ratio 16:9, total duration 20 seconds.
- The optical conceit — circular vignette, curved distortion — is described before any action, so it holds for the whole clip.
- A single fixed viewpoint means every change has to come from performance, which keeps the idea readable.
- Warm sconce lighting in a carpeted corridor gives the fisheye something with depth to distort.
1970s Mediterranean 16mm Documentary
A vertical clip styled as forgotten 1970s 16mm archival footage, complete with faded color, gate weave and shoulder-mounted imperfection.
Style: Authentic late-1970s Mediterranean documentary captured on vintage 16mm Kodak film, naturally faded colors, subtle film grain, real optical imperfections, slight gate weave, shoulder-mounted handheld camera with imperfect human movement, soft vintage lenses, warm afternoon sunlight, realistic skin texture, no cinematic polish, feels like forgotten archival footage discovered decades later. 0–3 seconds: A close handheld tracking shot follows a young woman in her 20s walking slowly through a narrow seaside alley lined with whitewashed houses, hanging linen curtains gently moving in the ocean breeze. She wears a simple linen dress, a woven shoulder bag, and naturally messy hair with no makeup. Instead of posing, she lightly brushes her fingertips across the textured walls while quietly observing everyday life around her. 3–7 seconds: The camera naturally falls slightly behind her as she enters a tiny open courtyard where local people casually gather. An elderly man repairs a bicycle, someone waters colorful plants from a balcony above, laundry sways overhead, and a sleepy orange cat crosses directly in front of the lens. The camera subtly adjusts to avoid the cat, creating an authentic human reaction. 7–11 seconds: A young child runs toward a rolling wooden toy that passes close to her feet. She instinctively bends down, catches it with one hand, smiles warmly, and hands it back without stopping her walk. The child laughs and runs away. No one performs for the camera; everything feels naturally observed. 11–15 seconds: She reaches a small overlook facing the sparkling sea. Instead of stopping dramatically, she casually rests one elbow on an old stone railing while watching distant fishing boats. A gust of wind lifts loose strands of hair across her face. She gently moves them aside and continues walking out of frame as the handheld camera hesitates for a second before slowly following behind. Image Quality: Ultra-photorealistic vintage documentary, authentic analog exposure, realistic human motion, organic focus breathing, imperfect framing, Kodak 16mm archival texture, subtle light leaks, soft highlight bloom, natural skin pores, no AI smoothness, 4:3 aspect ratio.
- Film artefacts are named individually — grain, gate weave, optical imperfections — instead of asking for a vintage look.
- Shoulder-mounted handheld is a physical description, so the motion has the right weight and hesitation.
- Framing it as footage discovered decades later tells the model to avoid modern polish everywhere, not just in the grade.
Planetarium Moon Gravity Horror
A projected moon in an abandoned Art Deco planetarium becomes physically real and pulls the whole auditorium into its gravity.
An elderly night janitor cleans an abandoned Art Deco planetarium during a thunderstorm. The projected moon becomes physically real and drags the entire auditorium into its gravity. [0–1.5s] Shot 1: Macro shot of mop water trembling in its bucket although the floor is still. [1.5–3s] Shot 2: Wide tracking shot follows the janitor beneath the dark planetarium dome. [3–4.5s] Shot 3: Close-up as the dormant star projector switches on by itself. [4.5–6s] Shot 4: Overhead shot: a perfect moon appears on the dome, shedding fine silver dust. [6–7.5s] Shot 5: The janitor’s flashlight beam bends upward toward the moon. [7.5–9s] Shot 6: Close-up of auditorium seats vibrating as loose screws rise from their mountings. [9–10.5s] Shot 7: Low-angle shot as the projected moon swells into a solid cratered sphere descending from the ceiling. [10.5–12s] Shot 8: The janitor falls upward, catching a brass handrail before leaving the floor. [12–13.5s] Shot 9: Popcorn, tickets and cleaning cloths spiral around the moon in orbital rings. [13.5–15s] Shot 10: Camera rolls ninety degrees as gravity rotates through the auditorium. [15–16.5s] Shot 11: Mop water climbs from the bucket as a transparent floating ribbon. [16.5–18s] Shot 12: Wide shot as seats tear loose and orbit without colliding with the janitor. [18–19.5s] Shot 13: The dome surface fractures into a convincing infinite star field. [19.5–21s] Shot 14: A miniature eclipse shadow begins crossing the moon and freezing everything it touches. [21–22.5s] Shot 15: The janitor swings between floating seats toward the emergency dome lever. [22.5–24s] Shot 16: Close-up: his fingertips catch the lever as the handrail tears loose. [24–25.5s] Shot 17: He pulls it; mechanical shutters race across the dome and extinguish the artificial sun. [25.5–27s] Shot 18: The moon implodes silently into streams of silver dust and collapsing orbital debris. [27–28.5s] Shot 19: Gravity returns; seats slam into place while the janitor lands safely in his rolling bucket. [28.5–30s] Shot 20: Quiet final close-up: he discovers a marble-sized moon in his pocket while the water in his bucket produces a tiny tide. Global style: Photoreal celestial surrealism, physically accurate dust and fluid behavior, deep blacks, silver-blue moonlight, Art Deco brass, realistic collision physics, coherent janitor identity. Effects must originate from the projector, affect real objects, then collapse into the miniature moon. No text, extra people or unexplained teleportation.
- The premise is stated in one sentence before the shot list, so every shot has the same physical rule to obey.
- Opening on trembling mop water establishes the invisible force before anything visibly happens.
- Numbered shots with timecodes keep an escalating physical effect from arriving all at once.
Baggage Carousel Hermit Crab
A midnight airport baggage carousel assembles itself into a giant mechanical hermit crab while the cleaner stays stranded on its shell.
A deserted international airport baggage hall after midnight. One tired cleaner in a blue maintenance uniform polishes the floor beside a silent oval baggage carousel. The carousel transforms through physically connected airport machinery into a gigantic mechanical hermit crab while the cleaner remains trapped on its rotating luggage-covered shell. Surreal horror-comedy, realistic industrial mechanics, cold fluorescent lighting, polished-floor reflections, thin cleaning mist throughout. One continuous unbroken 30-second Steadicam shot; no cuts, transitions, montage, teleportation or camera resets. The camera constantly travels forward through the transformation, changing composition organically as objects pass near the lens. 0.0–1.2s — Beat 1: Extreme close-up of the carousel reflected in the wet polished floor; one red warning light unexpectedly blinks. 1.2–2.4s — Beat 2: Camera tilts up to the sleepy cleaner leaning on his mop as the belt clicks once behind him. 2.4–3.6s — Beat 3: The carousel suddenly runs backward; the cleaner slowly turns, confused. 3.6–4.8s — Beat 4: Camera arcs around him while suitcases accelerate and their wheels chatter against the belt. 4.8–6.0s — Beat 5: A passing suitcase hooks his mop and pulls him onto the moving carousel. 6.0–7.2s — Beat 6: Camera follows beside him at belt speed as he runs helplessly between circling luggage. 7.2–8.4s — Beat 7: Security trays snap open and closed like small warning claws as they pass close to the lens. 8.4–9.6s — Beat 8: Camera dives through a gap between suitcases into the dark maintenance space beneath the carousel. 9.6–10.8s — Beat 9: Locked close tracking beneath the machinery: foundation bolts rotate loose and fire from the concrete. 10.8–12.0s — Beat 10: Conveyor supports unfold sequentially into six heavy segmented legs, each foot slamming down behind the advancing camera. 12.0–13.2s — Beat 11: The camera rises with the lifting structure as the entire carousel tears free from the floor. 13.2–14.4s — Beat 12: The oval conveyor twists vertically into a rotating spiral shell without breaking apart. 14.4–15.6s — Beat 13: Suitcases lock across the spiral one after another, forming mismatched shell armor. 15.6–16.8s — Beat 14: Two baggage scales hinge outward into broad mechanical claws. 16.8–18.0s — Beat 15: Departure monitors extend on flexible cable stalks and become expressive rectangular eyes. 18.0–19.2s — Beat 16: The completed hermit crab drops onto all six legs; the impact sends a circular wave through the floor mist. 19.2–20.5s — Beat 17: Camera tracks backward at floor level as the enormous creature scuttles sideways through the terminal. 20.5–21.8s — Beat 18: The cleaner circles overhead on the rotating shell, gripping his mop and passing above the lens once per revolution. 21.8–23.1s — Beat 19: The crab delicately lifts one suitcase and places it into an airport security tray while still moving. 23.1–24.4s — Beat 20: The exit scanner flashes red; the creature freezes and its monitor eyes glance nervously at each other. 24.4–25.7s — Beat 21: Passing overhead, the cleaner desperately scans his mop handle; the gate turns green with a cheerful chime. 25.7–27.2s — Beat 22: The crab ducks beneath the sign and squeezes through the exit, its luggage shell scraping sparks from the doorway. 27.2–30.0s — Finale: Camera glides backward through the automatic doors into the rainy airport forecourt. The crab emerges majestically, pauses in the mist and raises both claws. The cleaner stands on the rotating shell holding his mop like a victory flag. The monitor eyes blink proudly as one lonely suitcase arrives late through the doors and clicks perfectly into the final empty space in the shell. Sound: Continuous airport room tone evolving into conveyor rumble, suitcase-wheel percussion, hydraulic locking, concrete fractures, scanner beeps and deep mechanical crab vocalizations. Calm automated announcement during the chaos: “Your baggage has arrived.” Finish with the security chime and a strangely triumphant orchestral chord. Continuity constraints: Preserve one cleaner, one mop, one terminal layout and one mechanically coherent crab throughout. Every component must originate visibly from the carousel or surrounding baggage equipment. Maintain continuous screen direction and spatial geography. No organic flesh, extra limbs, duplicated luggage, changing uniform, illegible foreground text, gore or unexplained morphing.
- The transformation is required to use physically connected airport machinery, so the creature is built from things already in frame.
- Keeping the cleaner on the moving shell gives the audience a fixed human scale reference throughout.
- Cold fluorescent light and floor reflections stay constant, which lets the impossible geometry read clearly.
1980s Practical-Effects Horror Chaos
A square-format 1980s horror sequence made from squibs, rubber tentacles and physical stunts, cut fast enough to disorient.
1980s film, authentic live-action footage shot on 35mm with heavy grain, vibrant yet gritty saturated colors, practical neon lighting mixed with harsh strobes and fog. Fast chaotic editing packed with abrupt cuts, glass reflections, POV inserts, strobe flashes and dynamic movement to create total disorientation and panic. Real practical squib blood, rubber tentacles and physical stunts. Period-accurate 80s performances: big hair, colorful outfits, leg warmers, exaggerated fear and desperate physicality. Visualized synth atmosphere through pulsing lights and sudden dead silence. [IMAGE REFERENCES] Generate from scratch a consistent group of five mid-80s young adults with distinctly different looks—tall blonde mullet guy in neon shirt, short chubby dark-curly guy in Hawaiian print, slim big-curled redhead girl in neon dress, athletic black-ponytailed girl in crop top, lanky glasses brunette in pastel polo—in colorful yacht-party fashion and one original giant octopus killer with thick rubber tentacles and gaping beak. All on a neon-drenched luxury yacht in pure practical 1980s slasher style. [TIMELINE SECOND BY SECOND] 0-3s: [Rapid Disorientation Montage] Quick jarring cuts on the dimly lit yacht deck at night. Neon lights pulsing, five friends laughing and dancing with drinks, music blasting. Inserts: champagne spilling, one girl’s smile fading as mist rises from the water, glass reflection briefly showing a massive tentacle that vanishes. Strobe flicker. Laughter dies as engines are dead and no land in sight. 3-6s: [Rising Panic Montage] Fast cuts as panic spreads. Tall blonde runs to the helm, radio smashed. Close-up of broken mic. Two girls huddle near railing, eyes wide, calling names that echo. Low-angle POV gliding through thick fog. Drink glass tips. They split—one to cabins, one to stern. Water reflections show tentacles moving unseen. 6-9s: [First Attack Sequence] Sudden violence, rapid-fire cuts. Giant octopus erupts from foggy water. Quick cuts: massive tentacle lit by strobe, slamming down, bright squib blood spray across pink jacket. Body drops hard on wet deck. Others scream and scatter, slipping. One girl falls. Octopus advances with heavy tentacle movements while neon keeps pulsing. 9-12s: [Full Chaos & Practical Kills] Frenzied montage. Multiple cuts: guy racing for life raft, tentacle appears behind him. Girl hides behind bar, tentacle smashes through, practical blood on counter. Another cornered against cabin wall, lifted and slammed, body slides leaving red streak. Feet scraping, bodies falling, fog swirling around practical gore. Violent strobes. Survivor swings boat hook, dull thud on tentacle. 12-15s: [Climax & Lingering Threat] Fast cuts. Last two desperately lower a life raft. One yanked into fog and water, scream cut short. Final girl turns, face sweat-and-blood covered, backing on slippery deck. Wide shot of yacht littered with bodies under pulsing neon. Octopus rises again, tentacle cracked but massive. She runs into darkness as strobe freezes on the gaping beak. Slight film burn at end. [STYLE & QUALITY BOOSTERS] Photorealistic 1980s film emulation, heavy natural grain and reel artifacts, authentic practical squib blood and rubber-tentacle stunts, coherent physics with realistic slips and momentum on wet wooden deck.
- Asking for practical effects by name — squibs, rubber, stunts — rules out the clean CGI look models default to.
- Period accuracy is specified through performance and wardrobe, not just grade, so the era holds.
- Strobes, fog and glass reflections give the fast cutting something to break up, which is what creates the panic.
Dubstep Photo Animation Edit
Fourteen still photographs animated into a beat-locked dubstep edit where every cut, punch-in and movement hits the supplied track.
Create a fast, trippy 30-second dubstep music video using all the uploaded photographs (PLEASE FIND ATTACHED ALL 14 IMAGES + AUDIO IN THREAD). Use the uploaded 30-second audio as the only soundtrack. Make it a powerful dubstep edit: every movement, punch-in, transition and hard cut must hit the beat. Fully animate everything inside the photographs. Make the dancers perform, fabric and flames spin, painted eyes react, masks lunge, multiple arms ripple, the drummer strike his drum, sadhus dissolve into ash and black birds, motorcycles race aggressively, smoke creatures come alive, the underwater band actively play, boats move through the surreal landscape, and the flaming weapon create violent circles of fire. No photograph should remain static.Freely mix all the visuals in whatever order works best with the music. Let movement from one photograph naturally transform into the next: spinning fire becomes fabric, fabric becomes a painted eye, expanding arms become the drummer’s arms, ash birds become racing motorcycles, motorcycle dust becomes dancing smoke, smoke becomes underwater bubbles, bubbles become water and boats, and the boats transform into circles of fire.Keep constant movement throughout. Use rapid punch-ins, speed ramps, bass-impact flashes, hard rhythmic cuts, brief freeze-frames and fluid psychedelic transitions. Add a separate graphic layer flashing ॐ, the trishul, damru, third eye, crescent moon and traditional Hindu sacred symbols precisely on the beat. Let them pulse, rotate, distort and dissolve without covering the performers.Make it stylish, colourful, strange and extremely high-energy—an edgy, award-winning Incredible India advertisement edited like a dubstep music video. No dialogue, no typography, no slideshow, no long static shots and no complicated story. Finish with the strongest collision of fire, ash, birds and sacred symbols on the final bass hit. #capcutseedance25 #capcutcpp
- Supplying the audio and naming it the only soundtrack gives the model a fixed rhythmic grid to cut against.
- Each photograph is given a specific thing to animate — fabric, flames, painted eyes — instead of a blanket animate everything.
- Requiring every transition to hit the beat turns the edit itself into the choreography.
Locked Illustration Creature Story
An illustrated creature world animated forward continuously, with art style, palette and every character design frozen exactly as drawn.
Lock the original illustration completely. Preserve the exact art style, brushwork, textures, material rendering, color palette, creature proportions, facial expressions, lighting, composition, and every character design exactly as shown. Never change the visual style. Every creature must remain identical in every shot. No text, watermark, logo, or signature. One continuous story. Motion always progresses forward. No creature moves backward. Use cinematic pacing with hard cuts, speed ramps, bullet time, dynamic tracking, volumetric water, realistic physics, motion blur, subtle film grain, dramatic lighting, lens droplets, cinematic depth of field, bold camera language, emotional facial animation, and seamless transitions. 0-3s Without warning, the peaceful group suddenly notices every bird exploding into the sky. Tiny ripples appear beneath their feet. A deep rumble grows louder. Extreme close-up of frightened eyes. Fast push-in toward the rabbit. Hard cut to a gigantic wall of water rising behind them. Lightning-fast whip pan reveals the impossible tsunami racing toward the camera. Deep bass hit. 3-6s The wave crashes over everyone. Water engulfs the frame. Camera tumbles underwater with bubbles, debris, flowers, leaves and sunlight cutting through the current. Every creature is separated naturally by the force. Slow-motion for one second before time accelerates again. 6-10s Rapid cross-cut survival sequence. The rabbit paddles frantically with long ears floating behind. The lion powers through the waves with strong strokes. The rhino kicks heavily while struggling to stay above water. The giant blue triceratops swims like a massive whale. Frogs leap from floating debris. Tiny creatures cling to drifting branches. Cats desperately paddle while trying not to sink. Dynamic handheld water-level camera alternating with overhead drone shots. 10-15s The current becomes more violent. Floating logs collide. The turtle spins helplessly in a whirlpool before escaping. The sheep nearly slips beneath the surface until the lion nudges it upward. The black cat loses its grip and disappears beneath a wave. Silence for half a second except muffled underwater sound. 15-20s The gray kitten dives underwater searching. Cinematic underwater tracking follows the kitten weaving between drifting plants and bubbles. A frightened turtle struggles below. The kitten reaches it, grabs its shell with tiny paws and guides it upward toward sunlight breaking through the surface. 20-25s Both burst above the water. The exhausted kitten climbs onto the turtle's shell. The turtle begins swimming steadily through the endless flood while the kitten balances carefully, soaked but relieved. Around them every animal continues fighting the current in its own unique way. Long aerial tracking shot follows their path. 25-28s The current slowly weakens. One by one the surviving animals regroup behind the turtle. The rabbit swims beside it. Frogs hop onto floating wood. The lion keeps everyone together. The enormous blue triceratops shields the smaller creatures from remaining waves. Warm sunlight finally pierces the storm clouds. 28-30s A majestic vertical drone shot rises high into the sky. The flood forms beautiful winding rivers across the landscape. At the center, the tiny kitten sits safely on the turtle's shell leading the group forward while every surviving creature follows behind. The music swells into an emotional orchestral finale. Hold the final frame like an animated movie poster as golden light reflects across the water.
- The lock list is exhaustive — brushwork, materials, proportions, expressions, composition — closing every drift path.
- No creature moves backward is an unusual but effective constraint that keeps the story pressing forward.
- Banning text, watermark and signature keeps artefacts from the source artwork out of the render.
Japanese Obstacle Course Broadcast
Fake broadcast footage of a Japanese obstacle course show, built from ENG, crane, wire and telephoto camera coverage with early-HD softness.
Broadcast footage from a real 2000s–2010s Japanese sports entertainment program. Realistic TV broadcast footage reminiscent of a major Japanese obstacle course competition show. Full-scale sports coverage combining ENG cameras, crane cameras, wire cameras, and telephoto cameras. Natural handheld camera shake, zoom, pan, and tracking shots. Slightly soft footage characteristic of early HD broadcasts, natural broadcast noise, TV compression feel, realistic color reproduction. The venue features large lighting, spectator seating, announcer's booth, and the enthusiastic cheers of the heated audience. A tense atmosphere of anticipation and the challenger's seriousness permeate the entire competition venue. Fix the main subject completely to @[Image 1](image_1). Do not change the reference image's character's facial features, hairstyle, skin tone, body type, sense of age, expression, clothing, or identity from start to finish. Do not shift to a different person midway through generation. Maintain the hairstyle, face contour, eye and nose features, and body proportions. The outfit is based on the reference image and does not change even during the competition. 0–2 seconds [膝アップ紹介ショット / Knee-Up Introduction Shot] Challenger introduction via ENG camera. The character from @[Image 1](image_1) stands at the starting point, giving a natural smile and lightly waving to the camera. Applause and cheers rise from the venue. The background shows a massive obstacle course and spectator seating. A heated atmosphere as if the play-by-play announcer is introducing the challenger. Just before the starting buzzer sounds, the challenger turns forward and switches to a serious expression. 2–5 seconds [ワイドクレーンショット→追従カメラ / Wide Crane Shot → Tracking Camera] At the sound of the starting buzzer, they burst into a full sprint. They dive into the quad steps, nimbly navigating the diagonally placed footings on left and right with rhythmic steps. Arms swinging powerfully, conquering the obstacles with precise footwork. Roaring cheers from the spectator seats. Large lighting illuminates the entire course. 5–8 seconds [望遠トラッキングショット / Telephoto Tracking Shot] A big leap from the final footing, landing on the rolling hill (giant rotating roller). The roller begins spinning vigorously. The character from @[Image 1](image_1) spreads both arms wide to maintain balance, advancing cautiously yet swiftly. Their foot slips slightly, eliciting a murmur from the spectator seats. 8–11 seconds [高速サイドトラッキングショット / High-Speed Side Tracking Shot] The roller's rotation speeds up. The character from @[Image 1](image_1) desperately presses forward, but their right foot slips, causing their body to sway dramatically left and right. They swing their arms widely to regain balance. Realistic friction expression as the shoes skid across the roller surface. The commentary ramps up in excitement all at once. 11–13 seconds [斜め前方ダイナミックショット / Diagonal Front Dynamic Shot] They jump to leap to the next footing. However, the rotating roller catches their landing foot, causing their body to lose balance dramatically. They stretch both arms out to steady themselves but can't hold on, falling straight into the water hazard area. Screams and cheers mix from the spectator seats. 13–15 seconds [インパクトフォーカスショット / Impact Focus Shot] The character from @[Image 1](image_1) plummets spectacularly into the water hazard area, sending up a massive splash. They surface from the water, catching their breath with a rueful smile. Soaked to the skin yet showing a refreshingly sportsmanlike expression. Applause and cheers come from the spectator seats, as the play-by-play announcer wraps up the challenge in an excited voice. Video Quality・Style Faithfully recreate a 2000s–2010s Japanese sports program. Realistic ENG cameras, crane cameras, wire cameras, telephoto lenses for full-scale TV coverage. Natural zoom, pan, tracking shots. The soft texture of early HD broadcasts, natural broadcast noise, TV compression feel, color reproduction like live-action footage. Immersive feel from large lighting, realistic spectator seating, commentary, and cheers. Progresses throughout in real-time broadcast pacing, with no slow-motion effects used at all. Most Important Matters Maintain 100% of the character from @[Image 1](image_1)'s identity. Retain the face, hairstyle, body type, skin tone, sense of age, and clothing until the end. No becoming a different person, face deformation, or body type changes allowed. Do not display telops, program logos, watermarks, or subtitles. Do not display real program logos or trademarks. Realistic broadcast quality as if televising an actual Japanese obstacle course competition program. Camera work should resemble actual sports coverage, maintaining natural zoom, pan, and tracking shots.
- Listing the actual camera types used in sports coverage produces the multi-angle grammar broadcast footage has.
- Compression artefacts and broadcast noise are requested deliberately, which is what dates the footage correctly.
- The era is pinned to a range, so the model picks period-consistent graphics and framing.
Lunar Café Black-and-White Arthouse
A 1960s European café film shot in high-contrast monochrome, lit only by practicals plus cold light from the lunar plain outside the window.
META STYLE Black-and-white 35mm arthouse cinema, 1960s European café-film look. High-contrast monochrome, soft film grain, gentle bloom on the lamps, shallow depth of field on close-ups. LIGHT Night interior lit only by practicals: hanging globe lamps, the espresso machine's glow, and cold light through the window from the lunar plain. Soft key from the window side, deep shadow in the corners, clear catch-lights in the eyes. COLOR None. Full grayscale, rich mid-grays on skin, no tint of any kind. TEXTURE Fine grain. Chrome holds soft rolling reflections, glass refracts the lamps in small bright points, skin keeps visible pore-level texture with no smoothing. MOOD Quiet, intimate, unhurried — a conversation overheard in a place that is ordinary to the people in it. SCENE CONTEXT A near-empty late-night café on the surface of the moon. A man and a woman sit across a small round table beside the wide window, talking about the water. Neither of them ever looks outside. CHARACTERS The woman: early thirties, dark bob haircut, intelligent face, dark turtleneck with the cuffs visible at her wrists, thin earrings, light coat over her chair. She sits camera-left. Identical in every shot. The man: mid-thirties, dark slightly messy hair, light stubble, shadowed under-eyes, dark jacket over an open-collar light shirt, jacket sleeve visible at his wrists. He sits camera-right. Identical in every shot. LOCATION MAP Foreground: their small round table. Her espresso cup and the single tall glass of water sit on her side, close to her right hand. His espresso cup and spoon sit on his side. Nothing else on the table. Midground: small round tables, worn tiled floor, hanging globe lamps, chrome espresso machine at the counter. Background: a wide window along the wall beside them. Beyond the glass, a grey lunar plain with low craters, black sky, and Earth small and low near the horizon. FIRST FRAME / BLOCKING Interior medium two-shot, 47°, eye level. The woman sits camera-left, the man camera-right, the window and lunar plain behind them, café interior deeper in the room. Her hands are around her cup with the water glass beside it, his forearms rest on the table. FORMAT MODE Timed multishot with HARD CUTS only at 6.0s, 8.5s, 11.0s, 13.0s, 16.0s, 19.0s, 22.5s, 25.0s and 28.0s. The camera cuts only at these points. STORYBOARD SHOT 1 (0.0–6.0s) Medium two-shot, 47°, faint 1–2 cm breathing drift. The woman, eyes on him: "Do you think people get more honest when they're tired?" The man answers late, eyes coming up off the table: "No. Their lies just get less inventive." SHOT 2 (6.0–8.5s) Extreme close-up, 12°, of the woman's hands on her side of the table, dark turtleneck cuffs at her wrists. Her fingers leave her cup, lift the tall glass of water, and set it back down in the same place, the water rocking once. The woman, speaking over the image: "It's different tonight." SHOT 3 (8.5–11.0s) Close portrait of the man, 18°, eyes down. The man: "They changed the water." SHOT 4 (11.0–13.0s) Extreme close-up, 12°, of the man's hand on his side of the table, dark jacket sleeve at his wrist, turning his spoon a half-turn on the saucer. The woman, speaking over the image from off-frame: "Again?" SHOT 5 (13.0–16.0s) Medium close-up of the man, 29°, lunar plain soft behind his shoulder, eyes still on his cup. The man: "The old one remembered too much." SHOT 6 (16.0–19.0s) Close-up of the woman, 18°. Her eyes come up and hold his. The woman: "Water can't remember people." SHOT 7 (19.0–22.5s) Medium close-up of the man, 29°. He swallows once, then looks up at her. The man: "Probably not. But people can't remember the past either." SHOT 8 (22.5–25.0s) Medium two-shot, 47°, lunar plain behind them. She leans in slightly. The woman: "Then what do we remember?" SHOT 9 (25.0–28.0s) Close portrait of the man, 18°. One breath, then his eyes come up and hold hers. The man: "The last version we could live with." SHOT 10 (28.0–30.0s) Close-up of the woman, 18°, the lunar plain and black sky soft behind her through the glass. No dialogue. Her face stills, one slow blink, her eyes drop toward her cup and then drift slightly aside. The shot holds on her to the last frame, the image staying full and lit. PERFORMANCE Both faces stay mostly still, so small movements read. Emotion comes through eyelids, brow corners, jaw and breath rather than expression. Blinks work as punctuation — withheld through the important lines, released after. She runs from light and half-joking, to quieter, to genuinely curious, to quiet recognition at the end. He runs from dry amusement, to flat matter-of-fact, to unguarded tiredness on the last line. Living eyes with catch-lights, natural skin, precise lip sync whenever a speaking face is in frame. Every line is delivered unhurried and complete inside its own shot. PHYSICS Steam curls off the cups and the espresso machine. Water rocks and settles in the glass. The cup meets the saucer with weight, the spoon rings faintly on chrome. Nothing beyond the window moves. AUDIO The low hum of an enclosed room, a faint air-system whisper, the hiss of the espresso machine, a spoon against a saucer, a swallow of water. No music anywhere. Voices sit close and dry, as in a small room late at night. OUTPUT SETTINGS Black and white throughout, real-time, no slow motion. POSITIVE LOCKS The image stays fully monochrome in every shot. The woman speaks her five lines and the man speaks his five lines, exactly as assigned in the storyboard, and neither ever speaks the other's words. The single glass of water stays on the woman's side of the table for the whole scene, and only she touches it. The woman stays camera-left and the man camera-right in every two-shot. Hands in the extreme close-ups are identified by sleeve — turtleneck cuff for her, jacket sleeve for him. The table holds only two espresso cups on saucers, two spoons and one glass of water. The interior reads clearly as a café — table, cups, lamps, counter, espresso machine. The window shows a grey lunar plain, black sky and small distant Earth wherever it is visible, and nothing beyond the glass ever moves. Both characters keep their exact appearance and seats across every shot. All ten lines are spoken in full and finish inside their own shot. Cuts land only at the stated seconds. The video ends on the held close-up of the woman's face, the image full and lit to the final frame.
- Light sources are enumerated as physical fixtures, so the model lights the scene rather than applying a mood.
- Stating COLOR: None removes any chance of colour leaking into the grade.
- One incongruous element — the moon outside a period café — carries the concept without changing the film language.
Flooding Botanical Tower Ascent
A desperate climb up a flooding glass botanical tower, with each shot's subject position mapped explicitly inside the frame.
Scene and Mood: A lone figure climbs upward through a flooding vertical botanical archive tower during a night storm, glass tiers shattering and cascading water below, forcing a desperate ascent toward the glass dome roof as lightning flickers outside. Frame Map: Shot 1, seconds 0 to 6, subject small in the lower third of a tall vertical tower interior, tiers of glass terrariums stacked upward through the frame, water sheeting down from above. Shot 2, seconds 6 to 12, subject center frame climbing a metal service ladder bolted to the tower's inner wall, glass tiers visible left and right, water pouring past. Shot 3, seconds 12 to 18, subject in the right third crossing a narrow catwalk as a glass panel shatters in the left third behind them. Shot 4, seconds 18 to 24, subject small in the lower third reaching the dome's base, storm sky and glowing drifting spores filling the top two thirds through the glass ceiling above. Shot 5, seconds 24 to 30, subject silhouetted center frame bursting through the dome into open night air, lightning lighting the wider tower silhouette below. Subject Lock: One adult figure, lean build, soaked dark hair plastered to the forehead, a heavy canvas work jacket dark with water over a plain thermal shirt, fingerless work gloves, mud and plant matter smeared on one forearm. Posture straining and climbing throughout, gaze fixed upward, hands gripping rungs, rails, and glass edges with visible strain. Same face, hair, jacket, and build locked across all five shots, no change at any cut. Cross Frame Rules: Only one figure occupies every frame across the runtime, nothing else enters or crosses. Screen position shifts per the Frame Map, but soaked jacket state and climbing posture carry unbroken across every cut. Movement: Shot 1, subject wades through knee deep water at the tower's base then grips a ladder rung and begins climbing at second 4, water sheeting down past the shoulders, loose leaves and broken glass drifting past in the current below. Shot 2, subject climbs rung over rung, jacket heavy and dragging, a terrarium panel cracks audibly at second 9 sending a spray of water sideways past the frame. Shot 3, subject sprints across the catwalk at second 14, a glass tier shatters behind them at second 16 releasing a wall of water and debris that just misses their trailing foot. Shot 4, subject reaches the dome's base at second 20, presses both palms flat against the glass overhead, glowing spores drifting slowly against the dark storm clouds beyond it. Shot 5, subject drives a shoulder through the weakened dome glass at second 26, bursting into open air as lightning flashes and rain drives sideways, glass fragments scattering outward around them. Last Frame: Subject holds silhouetted center frame at the dome's broken edge, chest heaving, one hand still braced on the shattered frame, storm clouds and a bright lightning flash filling the upper half, the flooded tower's tiered silhouette dropping away below into darkness. No on screen text, no captions, no signage typography, no rendered text in the frame. World Plate: A tall cylindrical botanical archive tower at night during a storm, tiers of glass terrariums stacked vertically and lit faintly from within by dim growth lamps, water sheeting down the tower's interior walls, a narrow metal ladder and catwalk system running up the center. A glass dome caps the tower, storm clouds and lightning visible through it, faint bioluminescent spores drifting in the air near the ceiling. Sound Bed: Diegetic only, rushing water and heavy dripping throughout, metal rungs clanging under gripped hands, glass cracking and shattering at intervals, distant thunder rolling, wind howling as the dome breaks, heavy strained breathing and grunts of effort, rain hammering the outer glass, a final gust of wind once the dome opens. Capture Realism: Depth via suspended water mist and falling spray between the figure and the tiered glass planes behind them. Moisture without shine, soaked jacket and hair read matte and heavy, not glossy. Per zone specular kill on skin, wet skin reads diffuse, no beauty light glow. Contrast curve, controlled highlights on the lightning and growth lamps, lifted but not crushed shadow on the figure, mid tones held cool and desaturated throughout. Camera Capture: Wide latitude cinema capture, vintage 2x anamorphic character on Shots 1 through 3 at 35mm, handheld with restrained breath, shifting to clean spherical character on Shots 4 and 5 at 24mm, wider and harder shake against wind, fine 35mm grain, desaturated rendition crushed toward deep green and steel blue, 24fps natural 180 degree shutter blur, 30s total across five hard cut shots.
- A frame map assigns the subject a size and position per shot, so the vertical geography stays coherent.
- Rising water is a built-in clock, giving the sequence urgency without narration.
- Stacked glass tiers give every upward shot a repeating structure that communicates height.
Dance Studio Mirror Performance
A styled dance performance in a mirrored practice room, with wardrobe and grooming specified down to the hardware on the jacket.
Scene Polished man, early 20s, silver-white dyed comma fringe swept across forehead, subtle silver eye glitter on upper lids, small silver hoop in each ear. Outfit Cropped black leather jacket with silver zipper hardware over fitted white ribbed crop top, high-waisted straight-leg black leather pants, chunky black platform boots with thick rubber soles. Space Sleek professional dance practice room, floor-to-ceiling mirror panels on far wall, pale grey vinyl flooring with faint sheen, LED strip lighting mounted along ceiling perimeter and mirror frame edges cycling slowly cool blue ⇄ crisp white, immaculately empty ultra-modern minimalist. Camera Open Wide full-body at mid-chest height, 24mm equiv lens, slight low angle emphasizing boots and full silhouette. Color Grade High-contrast, cool cyan shadow toning, clean highlights. Mood Electric, controlled, precise. Diegetic SFX Throughout Boot strikes on vinyl, jacket leather creak on sharp arm movements, breath on exertion. Timeline 0s — Centered ready stance, feet hip-width, arms at sides wrists cocked outward, chest lifted, eyes forward to camera. Camera: hold static wide full-body LED: pulse once blue→white slow wash SFX: faint ambient room hum, vinyl floor creak under weight shift 3s — Sharp chest isolation pops forward+up x2, arms snap back simultaneously, chin lifts on each pop. Camera: wide with slight push in LED: cool blue intensifies at mirror edges casting twin reflections SFX: leather jacket creak on each arm snap 6s — Weight shifts right into crisp side-step lock — right foot steps wide, left foot locks behind at heel, both arms extend hard left in opposition creating diagonal line, head tilt left. Camera: rack to 3/4 angle showing dancer+mirror LED: white strip brightens sharply SFX: platform boot strike on vinyl — clean clap 9s — Double arm roll — both arms circle inward from shoulder in smooth rolling wave, hips counter-shift left, upper body undulates. Camera: slow push to medium full-body LED: fade briefly to dim blue creating moody strobe-adjacent flicker SFX: audible breath exhale at wave peak 12s — Body wave travels chest→hips→knees visible full-torso ripple, arms float wide, eye contact breaks as chin tucks then lifts. Camera: tilt slightly down to capture footwork on vinyl then return LED: brightens back to white SFX: rubber sole squeak on wave landing 15s — Right arm shoots forward with pointed index in sharp snap, left fist locks at hip, head snaps right, hold one beat then rapid alternating knee drops with hip emphasis, arms crossing low. Camera: pull wide to capture footwork and full-body bounce LED: strips cycle blue-white-blue rapidly SFX: two sharp boot strikes on alternating knee drops 18s — Explosive two-footed jump with tucked knees, arms flung overhead, hair catching air. Landing in deep crouch with arms slamming downward palms to floor, impact absorbed through knees. Camera: catch jump at apex then cut to low-angle looking up at landing LED: flare to full white on landing beat SFX: heavy dual boot impact reverberating 21s — 180° pivot on ball of left foot, right foot sweeping wide, arms open outward mid-rotation, full back shown revealing jacket back panel, then face returns chest proud. Camera: pan follow catching mirror reflection of turn LED: shifts to cool blue SFX: pivot foot scrape on vinyl 24s — Deep lunge right, right hand reaches toward floor without touching, left arm sweeps fully overhead, gaze locked to camera, torso twisted open. Hold one beat then pull to standing with controlled arm ripple outward from chest along both arms in fluid wave sequence. Camera: move to tight medium-body framing to capture arm ripple detail LED: pulses between blue and white rapidly SFX: leather creak on lunge-open 27s — Transition into sharp hip-isolation sequence, three crisp lateral hip pops L-R-L with upper body counter-isolating, arms frame-wide at shoulder height wrists flexed, speed increases. Camera: hold tight medium-body LED: holds bright white SFX: boot heel tap on each hip accent 30s — Final freeze, snap into wide-stance hero pose, right arm punched toward camera at shoulder height, left arm cocked at shoulder fist closed, chin angled down eyes lock directly into lens beneath silver comma fringe. All motion stops. Camera: hold medium full-body LED: lock to full cool blue casting sharp cyan shadows across vinyl floor, mirror behind reflects frozen pose doubled Diegetic SFX: silence drops completely; only faint room resonance remains
- Wardrobe is described as material and construction — cropped leather, silver zipper hardware, platform soles — which renders far more precisely than naming a style.
- Mirror panels give the model a reason to hold wide framing and show full choreography.
- Grooming details like eye glitter and hoops keep the identity stable through fast movement.
Hoverboard Desert Video Continuation
A direct continuation that starts on the exact last frame of a source video, carrying rider, board and desert world forward into new material.
SOURCE AND CONTINUATION Extend @video1. This is a direct continuation that begins at the exact frame where @video1 ends — the same ride, the same day, the next stretch of desert. Every shot below is new material that happens after the source footage, not a retelling of it. Preserve exactly from @video1: the rider's identity, helmet and visor, black riding suit, gloves and boots; the hoverboard and its cyan underglow; the desert world, dune shapes and haze; the low golden sun and its direction; the colour grade; and the music, which continues unbroken in the same key, tempo and arrangement with no restart. CHARACTERS The rider: same man from @video1, full dark helmet with a clear visor and two white light strips, black armored riding suit, gloves, boots. Identical in every shot. He rides the same hoverboard, lit underneath by a continuous cyan strip. LOCATION MAP Foreground: open sand, wind-carved ripples, loose grit lifting off the crests. Midground: the ride path — dunes flattening into a cracked salt pan that runs into a post-apocalyptic ruin field of collapsed concrete slabs, leaning steel columns, half-buried vehicle hulls and broken roadway sections. Background: a low sandstone cliff wall on the far side of the ruins, and beyond it open sky with the sun sitting low on the horizon. The rider travels camera-left to camera-right in every lateral view. The sun stays low and ahead of him, camera-right, throughout. FIRST FRAME / BLOCKING Full-frame lateral profile close-up of the rider, 18°, camera tracking alongside him at his own speed, his helmet filling the right third of frame in sharp profile, dunes streaking past behind him, cyan board glow spilling up onto his boots from below. FORMAT MODE Timed multishot with HARD CUTS only at 4.0s, 8.0s, 12.0s, 15.0s, 19.0s, 23.5s and 27.0s. The camera cuts only at these points. Real-time playback everywhere except 19.0–23.5s, which is slow motion; the speed change happens only on those two hard cuts. STORYBOARD SHOT 1 (0.0–4.0s) Lateral profile close-up, 18°, camera tracking beside him at 60 km/h, level with his shoulder. He rides steady, head turning a few degrees forward as the ruins come into his sightline, then his shoulders drop slightly and he leans in. Sand streams off the board's trailing edge behind him. Low sun rakes across the front of his visor from camera-right, leaving the far side of his helmet in deep shade. SHOT 2 (4.0–8.0s) HARD CUT to an extreme wide, 84°, camera high and static as he crosses the frame camera-left to camera-right at 60 km/h, a small figure with a cyan thread of light beneath him. Ahead of him the ruin field opens up — collapsed slabs and leaning steel standing as tall as six humans, throwing long shadows across the salt pan. SHOT 3 (8.0–12.0s) HARD CUT to a low tracking shot, 47°, camera 30 cm off the ground running with him at 70 km/h as he enters the ruins. He weaves between two leaning columns, board tilting hard onto its edge, a sheet of sand and grit fanning off the tail. Broken concrete passes close on both sides. Cyan underglow flares against the slab faces as he passes them. SHOT 4 (12.0–15.0s) HARD CUT to a medium shot from the front quarter, 29°, camera drifting backward ahead of him at 70 km/h. He drops into a deep drift, both arms out for balance, the board sliding sideways through a curve of debris, a long curtain of dust thrown out behind him and catching the low sun. His head stays locked on his line through the turn. SHOT 5 (15.0–19.0s) HARD CUT to a low rear three-quarter shot, 63°, camera accelerating with him from 70 to 110 km/h. He crouches, drives his weight forward, and the board's cyan strip brightens as it surges. Ahead of him a broken roadway section rises out of the sand at a shallow angle, its torn edge lifted clear of the ground. He hits it square and launches. SHOT 6 (19.0–23.5s) HARD CUT into SLOW MOTION. Wide side view, 47°, camera craning slowly upward with him against the low sun. He is airborne at the apex, board still under his feet, one hand gripping the front edge, knees folded. A full curtain of sand hangs suspended around and beneath him, every grain lit gold from camera-right and drifting rather than falling. The cyan glow underneath him rakes across the suspended sand. The whole shot stays in slow motion start to finish. SHOT 7 (23.5–27.0s) HARD CUT back to real time. Low tracking shot, 47°, camera behind and beside him. He lands hard, board slapping the sand and compressing, a burst of grit blowing outward from the impact, and he rides straight out of it at 110 km/h across the last open stretch toward the sandstone cliffs. The ruins fall away behind him. SHOT 8 (27.0–30.0s) HARD CUT to a lateral profile medium shot, 29°, camera settling alongside him and coming to rest as he does. He carves the board hard sideways and brakes, throwing a low wide sheet of sand forward and to camera-right, and stops at the cliff edge. He straightens up, squares his shoulders, and turns his helmet to face the sun sitting on the horizon. Held final frame: the rider in profile at the cliff edge, sand still settling around the board, the cyan glow steady beneath him, the sun low ahead of him. PERFORMANCE Everything reads through the body, since his face is behind the visor: weight shifting into each turn, arms counterbalancing the drift, the deep crouch before the launch, the folded stillness at the apex, the absorbed compression of the landing, and the settled straightening at the very end. Restrained and controlled throughout — a rider who knows this ground. PHYSICS The board carries real mass and inertia. It leans into turns and rebounds on landing. Sand behaves as loose dry grain: it fans off the edge under load, hangs in a curtain in slow motion, blows outward in a burst on impact, and settles slowly at the end. Dust catches and scatters the low sun. Wind drags loose grit off the dune crests continuously. Debris in the ruins stays put; only sand and dust move. LIGHTING Fixed 3200K golden-hour sun, low on the horizon ahead of the rider and camera-right, unchanged in every shot. Hard warm key on the front of his suit and visor, deep shade on the far side, long shadows running away camera-left across the sand and the ruin floor. Airborne dust glows where it crosses the sun. Cyan board light acts as a cold practical from below, catching his boots, the sand under him and nearby slab faces. AUDIO The music from @video1 continues unbroken through the whole extension — same track, same key, same tempo, no restart and no new song. Under it: the low hum of the board, wind across open sand, grit spraying off the edge, concrete and steel echoing close in the ruins. At 19.0s the mix thins for the slow-motion shot — the music drops to a single sustained low note, and the suspended sand and the board's hum sit at the front. At 23.5s the full arrangement returns hard on the landing impact. In the final shot the music resolves and holds under open desert wind. No dialogue anywhere. OUTPUT SETTINGS 16:9, real-time in every segment except 19.0–23.5s, which is slow motion. POSITIVE LOCKS This is a continuation of @video1 — all action takes place after the source footage ends. The rider, helmet, visor light strips, suit and the hoverboard's cyan underglow stay identical to @video1 in every shot. The rider travels camera-left to camera-right in every lateral view, and the sun stays low and camera-right in every shot. One continuous piece of music runs from the first frame to the last, carried over from @video1. The board keeps complete geometry and stays under his feet through the jump and landing. Cuts land only at the stated seconds, and the speed change to slow motion happens only at 19.0s and back at 23.5s. The video ends on the held profile of the rider stopped at the cliff edge, facing the low sun.
- Framing the task as continuation from an exact frame stops the model from re-telling the source footage.
- The carry-over list is explicit — identity, helmet, suit, board glow, world — so nothing resets at the seam.
- Declaring every shot to be new material after the source prevents accidental repetition of source beats.
Giant Versus Dragon Over the Lake
A colossal giant wades through a lake swatting at an aerobatic dragon, written as one short paragraph with no shot list.
A colossal giant appears, striding through a lake; the ground shakes with every step, sending massive amounts of water splashing. A flying dragon appears, performing aerial acrobatics; the giant tries to catch it with his arms, but the dragon manages to dodge the giant's attempts to stomp on it. A fast-paced action scene with realistic cinematography.
- Two creatures at wildly different scales give the model an obvious way to stage every frame.
- Ground shake and water displacement are named, so the giant's weight is visible rather than implied.
- The dragon's evasion supplies continuous action without needing choreography detail.
Gravity-Defying School Group Dance
A lead dancer walks through a school where gravity has no fixed direction, gathering students into an energetic group number.
【主体】 @Image1 のダンサー兼役者。参照画像の顔立ち・髪型・衣装を忠実に維持すること。周囲には学園の生徒たち多数（群舞メンバー）。 【シーン】 実写調の異世界の学園。重力の方向が判然としない不思議な空間（廊下や階段が斜めに交差し、上下感覚が曖昧）。背景の一貫性のみ保持し、カット間で同一の学園世界であることがわかるようにする。 【アクション】 主役が学園内を練り歩き、その動きに呼応して生徒たちが次々とダンスに加わっていく。ユーモラスでエネルギッシュなボリウッド風の群舞。ラストは全員が一箇所に集合し、フォーメーションを組んで踊り上がる。 【カメラワーク】 Fast-paced rhythmic cuts synced to music, tracking shot following the lead dancer, dynamic crane and dolly movements, wide shot for the final group formation. 【スタイル・雰囲気・仕様】 ボリウッド映画風のダンスムービー。軽快で情熱的なボリウッド音楽に合わせた高揚感のある演出。カラフルで彩度高め。24FPS。
- The impossible space is defined by a rule — corridors and stairs cross at angles with no clear up — rather than by individual shots.
- Dancers joining progressively gives the sequence a built-in escalation to the final formation.
- Only background consistency is required, which frees the camera to move dramatically between cuts.
Window Cleaning Morning Slice of Life
A young woman washes a house window onto a quiet alley in mid-morning light, styled deliberately away from any commercial polish.
Main Subject: Young Korean woman, early 20s, natural everyday appearance, oversized faded t-shirt tucked into shorts, hair tied up in a claw clip, minimal makeup, realistic skin texture, cheerful relaxed personality. Location: Small house window facing a quiet residential alley, mid-morning. Wooden window frame, a bucket of soapy water on the ledge, potted plants nearby, soft sunlight. No commercial elements. Visual Style: Ultra-realistic documentary realism, unscripted domestic feeling, soft natural morning light. Camera Style: Early 2000s consumer DV camcorder aesthetic, handheld shake, autofocus hunting between her and the glass reflections, faded soft contrast, mild sensor noise. No stabilization. Timeline (30 sec): 00:00–00:03 → She dips a cloth into the soapy bucket, then wrings it out over the ledge. 00:03–00:06 → She wipes the window in slow circular motions, streaks of soap catching the light. 00:06–00:09 → She pauses, then says to camera "이거 완전 뿌옇게 됐었어" ("This got really foggy"). 00:09–00:12 → She rinses the cloth again, then continues wiping the lower corner of the glass. 00:12–00:15 → She steps back to check her work, tilting her head side to side. 00:15–00:18 → She notices a smudge, then leans in to rub it out more carefully. 00:18–00:21 → She wipes her hands on a towel, then looks at camera saying "이제 깨끗하다" ("It's clean now"). 00:21–00:24 → She admires the clear view through the glass, smiling softly. 00:24–00:27 → A light breeze moves the curtain nearby; she glances at it, amused. 00:27–00:30 → She looks at camera saying "다음 창문도 해야지" ("I should do the next window too"), walking off as it fades. Audio: Cloth squeaking on glass, water dripping, faint birds, distant street sounds. Her dialogue as noted above. No music. Goal: A quiet, satisfying weekend chore moment grounded, warm, believable.
- Everyday styling is specified — oversized faded tee, claw clip, minimal makeup — so nobody looks cast.
- The location is small and specific, which keeps the scene from expanding into a set.
- Ruling out a commercial look prevents the model reaching for advertising lighting.
Graffiti Street MV with Randomised Scenes
A live-action style street music video where the model is told to randomise backgrounds and VFX from a fixed list while keeping the performer consistent.
参照キャラクター画像を1枚使用する。 参照画像の髪型、体型、衣装シルエット、表情の方向性、雰囲気を参考にする。 実写MV風の架空人物として自然に再構成する。 実在の俳優、モデル、有名人、特定の人物には似せない。 参照画像の衣装、色、アクセサリー、世界観をもとに、背景・VFX・色・記号・装飾をランダム生成する。 背景は固定せず、参照画像に合う実写MV風の場所をランダムに選ぶ。 屋上、路地、ステージ裏、廃ビル、夜の街、ネオン空間、グラフィティ空間、ライブ会場裏など。 全体はグラフィティ系実写MV風に統一する。 60fps。 118 BPM基準。 高品質な実写MV。 リアルな人物、肌、髪、布、アクセサリー、靴。 自然な照明と現実のカメラ質感。 背景には実写と馴染むグラフィックモーションVFXを重ねる。 ダンスは、男性にも女性にも似合う自然なストリート系MVダンス。 難しい技を連発しない。 人間が自然に踊れる範囲の動きにする。 脚を曲げ続けず、自然な立ち姿勢を保つ。 膝はビートのアクセントで軽く沈む程度にする。 重心移動、踏み替え、軽いターン、肩のリズム、手先の動きを中心にする。 動きはキレがあるが、ロボットのように硬くしない。 身体全体が音に乗って自然につながるようにする。 単純な横移動を主役にしない。 前後の奥行き、身体の角度変化、軽い踏み替え、自然なターンで見せる。 腕は振り回さず、身体に近い位置でスタイリッシュに動かす。 手首や指先は自然に使う。 過剰にセクシーにしない。 アイドルダンスにも、バレエにも、ロボットダンスにも寄せない。 背景とVFXは常に軽く動く。 参照画像の世界観に合う抽象記号、短い文字断片、模様、アイコン、スプレー跡、光の線、ノイズ、図形、装飾をランダムに配置する。 文字や記号の意味は固定しない。 VFXは人物の後ろで控えめに反応し、顔や身体を隠さない。 VFXは身体の動きに自然に反応する。 足の接地で小さな粒子や波紋が出る。 肩や手の動きに合わせて背景の線や光が軽く揺れる。 衣装の差し色から小さなスパークや色残像が出る。 布やアクセサリーの揺れに合わせて短い光の残像が出る。 演出は派手すぎず、実写MVに馴染ませる。 カメラは実写MVの自然なカメラワーク。 開始直後から中距離の全身ショット。 人物は映像開始時点ですでに踊っている。 カメラは完全停止しない。 軽い押し込み、軽い引き、斜め前からの小さな回り込み、短い足元カットを使う。 カメラを動かしすぎない。 ダンスのライン、衣装、表情が読めるように撮影する。 0.0s - 3.5s 開始直後から自然に踊っている。 中距離の全身ショット。 片足を軽く前へ踏み込み、ビートに合わせて上半身が自然に乗る。 肩を小さくヒットさせ、手首を軽く外へ流す。 足元は小さな踏み替えとつま先タップ。 膝は軽く使うだけで、曲げ続けない。 表情は参照画像の雰囲気を保つ。 背景VFXは軽く跳ね、足元に小さな粒子が出る。 3.5s - 7.0s カメラが斜め前から少しだけ押し込む。 人物はその場を中心に、前後の踏み替えと軽いターンで踊る。 腕は身体の近くでコンパクトに動かす。 片手を衣装ディテールの近くへ持っていき、軽く離す。 肩、胸、手首の動きが滑らかにつながる。 脚のラインが自然に伸びる瞬間を作る。 背景のランダムなグラフィックが音に合わせて揺れる。 7.0s - 10.5s 上半身を少し強調する。 短い視線、軽い首の角度変化、手先のフリックを入れる。 足元は大きく移動せず、踏み替えと小さなクロスステップでリズムを取る。 身体を少し斜めに向けてから正面へ戻す。 ターンは小さく自然にする。 VFXは衣装カラーに合わせて、光の線や粒子が控えめに反応する。 10.5s - 13.5s 動きを少しだけ強くする。 前後のステップ、肩ヒット、手首スナップ、軽い胸ヒットをつなげる。 一つ一つの動きは独立させず、身体全体の流れとして自然につなぐ。 膝は一瞬だけ沈め、すぐ自然に伸ばす。 背景グラフィックが少し活発になり、奥行き方向へ流れる。 13.5s - 15.0s 次の動きへつながる準備。 人物は前後のクロスステップと小さなターンを続ける。 最後に止まらない。 決めポーズにしない。 身体がまだ動いていて、次のステップへ入る途中で終わる。 背景VFXも止めず、奥へ流れるように動かす。 全体印象： 参照画像ベースのカラフルなグラフィティ系実写MVダンス。 自然に人間が踊っているような、滑らかで見栄えの良い振付。 男性にも女性にも似合う。 キレはあるが、硬すぎない。 脚を曲げ続けず、自然な立ち姿勢と軽い沈みを交互に見せる。 横移動を多用せず、前後の奥行き、角度変化、踏み替え、自然なターンで見せる。 開始直後からダンスで入り、次の動きへ繋がる途中で終わる。 テキストオーバーレイなし。 字幕なし。 ロゴなし。
- Giving the model a menu of allowed locations produces variety without losing tonal control.
- Specifying BPM and frame rate gives the choreography and cutting a concrete tempo.
- Asking for a fictional person inspired by the reference avoids resembling any real performer.
Vietnamese Mythic Creature Epic
A Vietnamese folklore epic pitting a peasant hero against a giant black guardian bird and a serpentine sea monster.
[Phần 1: Character] + Nhân (young man, @referance image): A rustic Vietnamese peasant with sun-bronzed skin, wearing simple dark linen garments, showing deep resilience and bravery. + Hắc Thần Điểu (mythical giant bird @referance image ): A colossal guardian bird of prey with jet-black feathers, a razor-sharp golden beak, and piercing, glowing red eyes. + Giao Long (mythical sea monster): Serpentine dragon-like sea creatures covered in dark green scales with vibrant bioluminescent green patterns and glowing eyes. [Phần 2: Bối cảnh] An ancient mythical Vietnamese seascape during a raging tempest, dominated by towering limestone karsts rising majestically from a turbulent, bioluminescent green ocean. The environment is devoid of any modern structures, filled only with untamed waters, dark ominous storm clouds, and a mythical atmosphere of a forgotten folkloric era. [Phần 3: Phong cách đoạn video] Cinematic 8K video style with hyper-realistic textures and dynamic dark-fantasy atmosphere. The color palette features deep ocean blues, stormy charcoal greys, and dramatic contrast from the vibrant bioluminescent green of the sea creatures and the divine gold energy of the mythical bird. High-speed action cinematography with dramatic slow-motion, dynamic tracking shots, shutter angle matching intense action, organic film grain, and realistic water simulation with volumetric splashes and heavy atmosphere. [Phần 4: Shot-by-shot] Shot 1 (2s): POV moving rapidly upward from deep underwater towards the surface. Looking through the murky, bubbling green water, the glowing silhouettes of giant Giao Long swirl below, creating a sense of thalassophobia. Above the water's surface, the dark silhouette of Hac Than Dieu 📷is visible from behind, flying in place with Nhan r📷iding on its back, his back turned to the camera. Golden hour stormy light filters through the surface. no dialog Shot 2 (3s): Close-up of the bubbling, boiling sea surface glowing with an eerie, underwater green bioluminescence under a dark stormy sky. The atmosphere is strangely silent. A colossal, glowing shadow of Giao Long swirls beneath the waves, then suddenly bursts violently upward from the ocean directly towards the camera, spraying water everywhere. no dialog Shot 3 (1s): Close-up of Nhan's panicked face under the flashing stormy light, wind whipping his hair. He sits on the back of Hac Than Dieu, quickly turning his head around to look at the newly emerged sea dragon behind them, his eyes wide with fear. Nhan screams "Cẩn thận!" (dialogue in Vietnamese). Shot 4 (1s): Close-up of Hac Than Dieu under the stormy sky, its sharp head snapping around in alarm toward the direction Nhan is looking, its red eyes glowing intensely as it senses the threat. no dialog Shot 5 (2s): Wide slow-motion tracking shot. Under a dark, stormy sky, the massive Hac Than Dieu, with Nhan clinging to its feathered back, masterfully tilts its giant black wings to the side, narrowly evading the massive Giao Long's snapping jaws in a near-miss aerial dodge. no dialog Shot 6 (2s): Slow-motion close-up of Nhan under flashing lightning, his expression filled with sheer terror as the bird tilts sharply. He grips the thick dark feathers of Hac Than Dieu tightly with both hands, trying his best not to fall off into the ocean below. no dialog Shot 7 (1s): Slow-motion extreme close-up of the lunging Giao Long's fearsome mouth, filled with sharp, wet fangs and glowing with green light, snapped open wide, attempting to bite the edge of Hac Than Dieu's massive black wing under the stormy sky. no dialog Shot 8 (2s): Slow-motion shot of Hac Than Dieu carrying Nhan on its back. The giant bird performs a breathtaking mid-air barrel roll under the dark, thundering clouds, its body twisting elegantly to dodge the attack. no dialog Shot 9 (4s): Wide shot showcasing the majestic landscape of jagged limestone karsts rising from the churning ocean. The bioluminescent green water glows intensely as multiple Giao Long rise and fly up. The camera speed ramps back to normal as Hac Than Dieu escapes the first bite spectacularly, swiftly dodging a second lunging Giao Long, while three more of the sea monsters are seen in the background preparing to lunge at high speed. no dialog Shot 10 (1s): Close-up of Hac Than Dieu's head under the stormy sky. The giant bird opens its sharp beak wide, letting out a booming, telepathic command. Hac Than Dieu shouts "Bám chặt!" (dialogue in Vietnamese). Shot 11 (1s): Close-up of Nhan. Shifting from initial panic to absolute focus, his face hardens with determination as he locks his grip even tighter onto the dark feathers of Hac Than Dieu under the flashing lightning. no dialog Shot 12 (1s): Medium shot under the dark stormy twilight. The first Giao Long, frustrated by its missed attack, turns around aggressively and lunges headfirst directly towards the camera, its glowing green eyes filled with rage. no dialog Shot 13 (9s): Medium dynamic continuous shot kết hợp với obit shot. Under the dark stormy sky, Hac Than Dieu carrying Nhan releases a brilliant burst of divine golden energy. Suddenly accelerating, the giant bird rolls in mid-air and strikes the lunging Giao Long's head with its powerful talons, knocking it out of the frame. Instantly, a second Giao Long attacks from the side; Hac Than Dieu swerves swiftly, and Nhan uses the momentum to land a powerful kick on the monster's flank, sending it crashing away. Two more Giao Long attack in tandem; a smooth, dynamic orbiting camera tracks Hac Than Dieu as it weaves through their strikes, diving through a narrow, majestic limestone mountain pass over the sea, leading the camera into a pitch black screen. no dialog
- Each mythic creature gets its own design paragraph, so they read as distinct beings rather than generic monsters.
- Writing character names in the local language preserves cultural specificity the model can draw on.
- The hero is described through material and bearing, which keeps him grounded against fantastical opponents.
Beauty Filter Comes Alive Comedy
A woman's over-filtered self climbs out of her phone and fights to leave the apartment first, until daylight destroys her.
【风格】高概念脑洞喜剧短剧（High-concept Filter-Comes-Alive Comedy），真人实拍质感（Photorealistic）+ 滤镜版数字失真特效，抖音竖屏9:16爆款，居家暖光转门口强逆光，2人出镜(同一张脸的两种状态) 【时长】30秒 【场景】女生出租屋玄关，暖黄灯光，全身镜、口红外套挂钩，门口一开就是刺眼的白昼阳光 【角色】真人版她 @图1（自然素颜感：真实毛孔、淡淡黑眼圈、发型随意，好看但真实）、滤镜版她 @图1同一张脸（过度美颜：磨皮到发光、瞳孔放大、锥子下巴、浓密假睫毛、皮肤像塑料，动起来偶尔有数字残影）——两人同脸，靠"真实/失真"区分 【核心机制】滤镜版从手机屏幕里活出来，与真人抢着出门，最后在强光下滤镜崩坏"见光死" [00:00-00:03] 钩子·屏幕里的她动了（怼脸手持自拍视角） 真人举着手机开满美颜疯狂自拍、嘟嘴比耶，然后放下手机准备去开门。手机屏幕里那个美颜版却没跟着放下——她自顾自托腮打了个哈欠，开口说话。 【台词】滤镜版（慵懒抱怨）：「哈——累死了，一直维持这个角度，你腮帮子不酸我酸。」 [00:03-00:06] 爬出手机（特写→中景） 真人吓得手机差点脱手。滤镜版扶着屏幕边框，像翻窗一样从手机里爬出来，落地伸个懒腰，浑身磨皮反光、假睫毛扇两下，数字残影一闪。 [00:06-00:09] 互相嫌弃（双人同框斗嘴） 滤镜版上下打量素颜真人，一脸嫌弃；真人也瞪着这个塑料脸的"自己"。 【台词】滤镜版（挑眉）：「就你这毛孔和黑眼圈也敢去见网友？今天，我去。」 她一把扯下挂钩上的外套。 [00:09-00:13] 门口拉扯（快节奏） 真人一把抢回外套，两人在玄关你拽我拉、互不相让，语速飞快。 【台词】真人：「他约的是我！」滤镜版：「他喜欢的是我这张脸！」 [00:13-00:16] 偷袭上位（反转铺垫） 门铃"叮咚"响。滤镜版趁真人分神，一把将她推到镜头外，自己迅速扶发、摆出完美角度，得意地去开门。 [00:16-00:20] 见光死（高能特效·全片核心） 门"唰"地拉开，刺眼的白昼阳光直射进来——滤镜版瞬间开始崩坏：脸忽大忽小、五官错位、皮肤打上马赛克、磨皮失灵露出诡异色块，整个人像信号极差的视频卡顿闪烁。 音效：一声刺耳的电流杂音+视频卡顿"嘟嘟"声。 [00:20-00:24] 网友后退（悬念处理） 门口来人(只给愣住的背影和后退半步的脚)被这鬼畜画面吓得倒退，一脸问号。滤镜版慌乱地想稳住脸，却越闪越离谱，发出机械故障音。 [00:24-00:27] 真人反杀 真人不慌不忙从旁边走进阳光里——素颜、真实、自然，反而在阳光下透亮好看。她一把拎起崩溃闪烁的滤镜版，像塞回垃圾桶一样把她按回手机屏幕里，拍拍手。 [00:27-00:30] 定格收尾 真人转头对门口的人自然一笑，阳光落在真实的脸上。 字幕（砸出）：「滤镜一时爽，见光就现形。」 音效：欢快BGM在滤镜崩坏时掐断留白，真人一笑时清爽音效"叮"，收尾。 【导演备注】1.创意机制铁律：两个女主必须是@图1同一张脸，靠"真实质感 vs 过度磨皮失真"强区分，绝不能长成两个人；滤镜版全程带极轻数字残影，为结尾崩坏埋线；2.见光死特效：滤镜崩坏只发生在门开、强光射入的瞬间，表现为马赛克/五官漂移/卡顿闪烁/塑料色块，像滤镜在强光下失效，是全片记忆点，前面不能提前崩；3.节奏铁律：屏幕说话→爬出→斗嘴→抢外套→偷袭→见光死→反杀一气呵成，每2-3秒一个新反应，不停顿；4.口型同步准确，斗嘴台词又快又冲；5.真人版结尾在阳光下要真实好看(不是丑)，立意是"真实>滤镜"，基调轻松不贬低任何人；6.门口来人只给背影/局部制造悬念，不露正脸。 【负面提示词】两个女主长成不同的人，真人版被拍丑/贬低身材，滤镜崩坏提前出现，见光死特效不明显，换脸(指两人互相变成别人)，口型不同步，表演僵硬夸张，塑料CG(除滤镜版故意的塑料感)，多余手指，字幕提前，水印，真实品牌logo，画面过度抖动，未成年人形象。
- Both versions share one face and are separated only by processing — real pores versus plastic smoothing — which makes the gag legible.
- The digital artefacts are given behaviour (occasional ghosting when moving) rather than being a static look.
- Harsh daylight at the door is set up as the punchline before it is used.
Thirty-Second Duo Dance in One Cut
A 30-second duo dance in a single unbroken take, with an explicit rule that the movement density must match a 15-second routine.
🕺プロンプト⬇️ Seedance 2.5｜30秒・完全ワンカット高速デュオダンス 30秒間ワンカット。編集カットなし。ショット切替なし。場面転換なし。別ショットへの変更なし。開始から終了まで同じ連続テイク。二人は常にフレーム内へ明確に収める。人物の複製、別人化、入れ替わり、融合、新しい人物の出現は禁止。 30秒だから動きを遅くしない。15秒ダンスと同等の運動密度を30秒間維持する。開始直後からすでに踊っている。静止、長いタメ、歩くだけの時間、ポーズを見せるための停止は禁止。約1拍から2拍ごとに、足、腰、胸、肩、首、腕、手首、指先、視線のどれかへ明確なアクセントを入れる。 キャラクターA：REN 20代半ばの東アジア系男性。高身長で細身だが、ダンサーらしく引き締まった体型。健康的な暖色系の肌。切れ長の琥珀色の瞳。目元へかかる、濡れたような黒いレイヤーヘア。挑発的で余裕のある表情。 浅く被ったヒョウ柄キャップ。アイスブルーとシルバーの光沢を持つ短丈デニムジャケット。内側には白いアシンメトリーなメッシュトップス。腰位置の高いライトブルーのダメージデニム。腰から揺れる赤いペイズリー柄の細長い布。複数のゴールドチェーン、細いベルト、腕時計、ブレスレット、メタリックパーツ。キャメル色の厚底ワークブーツ。 RENは動きの起点が鋭い。ヒールトゥ、高速クロスステップ、胸のヒット、肩の切り返し、手首スナップが得意。大胆で、相手を先に誘う。基本的に前半は半拍先行する。 キャラクターB：NOIR 20代後半の東アジア系男性。RENよりわずかに背が高く、華奢で手足が長い。色白の肌。細い黒縁眼鏡。灰黒色の鋭い瞳。片目へ落ちる無造作な黒髪。静かで妖しく、感情を表面へ出しすぎない。 黒と青紫の光沢を持つ短丈テーラードジャケット。細いシルバーライン。内側には少し透け感のあるオフホワイトシャツ。緩めた細い黒ネクタイ。高い腰位置の黒いワイドパンツ。左右非対称の揺れる布パネル。銀のチェーン、鍵型アクセサリー、細いボディベルト、指なし手袋。厚底の黒いレザーブーツ。 NOIRは肩、首、手首、指先、背骨の流れが柔らかい。RENの動きを半拍遅れて受け取り、そのまま模倣せず、反対方向や別の軌道へ変えて返す。中盤以降は先行役へ切り替わる。 二人の顔、髪型、肌色、体型、身長差、衣装、帽子、眼鏡、靴、装飾品を30秒間固定する。RENに眼鏡、黒いジャケット、銀の鍵飾りを追加しない。NOIRに帽子、青いデニム、赤い布、ゴールドチェーンを追加しない。二人の衣装や特徴を交換しない。 カメラ 中距離の全身ショットを基本にする。9:16の縦構図を活用し、一人を手前、一人を奥へ配置する前後構成と、二人を斜めに並べる構成を交互に使う。 カメラは30秒間完全停止しない。短い押し込み、軽い引き、小さな半円回り込み、わずかな上下移動、自然な手持ちの揺れだけで変化を作る。横方向へ長く移動するサイドスライドは禁止。 足元を見せる時もカットを切らず、カメラが少し低くなり、全身の中へ靴と足運びを含める。表情や手の接触を見せる時も、カメラが自然に少し押し込むだけにする。顔だけの長いアップは禁止。二人の脚とダンスを見失わない。 カメラはダンスを待たない。動作と同じテンポで小さく反応し、肩ヒットで微細に押し込み、ターンで短く回り込み、位置交換でわずかに引く。 アートステージ 背景は現実の場所ではない。屋上、路地、廃ビル、倉庫、普通の壁、夜景、街並み、写真背景のような風景は禁止。 実写MV用の巨大な縦型アートステージ。黒、オフホワイト、コバルトブルー、アイスブルー、深紅、鈍いゴールドを中心に構成する。 巨大グラフィティ、ネオンライン、手描き記号、意味を持たない抽象文字、動くポスター、破れた紙、スプレーアート、光る壁面、反射床、浮遊する紙片、黒インク、白い粒子、LEDライン、ステンシル、動く抽象図形を多層的に配置する。 開始時点から背景は激しく動いている。背景全体が118 BPMへ反応し、跳ねる、流れる、震える、剥がれる、反転する、再配置される。人物より前へ出ず、二人の顔、身体、脚を隠さない。 ステップで足元のグラフィティが弾ける。肩ヒットで壁の線が震える。胸ヒットでLEDが一度強く脈打つ。ターンで抽象記号が渦を作る。手首スナップで白いブラシ線と黒いインク斬撃が走る。指フリックで星形、稲妻、短いスパークが散る。接触動作では二人の間へ円形波紋が生まれる。 文字や記号を読ませる文章にはしない。歌詞、タイトル、字幕、ロゴ、ブランド名を表示しない。 ダンス全体 高速で華やかなストリートダンスと、親密なパートナーダンスを融合する。 細かな足踏みだけにしない。脚だけで踊らず、上半身、腰、胸、肩、首、腕、手首、指先、視線まで使う。高めの重心、綺麗な立ち姿、流れる連続動作を維持する。 低重心を長く続けない。膝はアクセントで一瞬だけ曲げ、すぐに伸ばす。しゃがみ込み、床ダンス、長い静止、重い動きは禁止。 二人は常に完全同期しない。半拍遅延、ミラー、逆方向への返し、交互の先行、短い完全ユニゾンを切り替える。 カップルダンス的な接触として、手首を受ける、前腕を組む、腕の下をくぐる、肩をかすめる、背中合わせになる、互いの重心を一瞬預ける、身体を引き寄せてすぐ離す、位置を交換する動きを使う。 接触後も止まらない。触れる、回る、離れる、次のステップへ入るまでを一つの連続動作にする。 0.0s–1.2s 開始直後から二人はすでに踊っている。 RENが手前、NOIRが約1.5メートル後方。二人とも中距離の全身。 RENが片足を前へ鋭く踏み込み、膝を一瞬使ってすぐ伸ばす。右肩ヒット、左肩ヒット、胸ヒット、手首スナップ。ヒールトゥからクロスステップへ入る。 NOIRは半拍遅れて同じ足運びを始めるが、腕はRENと反対方向へ流す。足元から粒子波紋と手描き円形波紋が広がる。 1.2s–2.4s カメラが短く押し込む。 RENが斜め向きへ切り替え、前後ステップ、首スナップ、腰の小さな切り返し。片手を胸元のチェーンへ流し、すぐ外へ弾く。 NOIRは半拍遅れて肩と胸を刻み、指先を顔の横から下へ切る。背景線が連続して震え、白いブラシ線が走る。 2.4s–3.6s カメラが少し低くなり、足元を含む全身。 二人が左右反転した高速ヒールトゥ。つま先タップ2回、かかとを引く、鋭いクロスステップ、斜め前への踏み出し。 RENが先に腰を小さく回し、NOIRが半拍遅れて逆方向へ回す。靴の軌道へ白線と粒子の尾が残る。 3.6s–4.8s 二人が前後位置を保ったままコンパクトなランニングマン変形。後ろへ引き、すぐ前へ戻る。 RENが腕を身体の近くから外へ切り、NOIRが逆側へ長く流す。二人が同時に小さくピボットし、視線だけをカメラへ向ける。 指フリックで星形とスパーク。巨大グラフィティが波打つ。 4.8s–6.0s カメラが小さく半円回り込み、二人が斜めに並ぶ。 RENが片足クロス、反対足オープン、胸ヒット、肩抜き。NOIRは半拍遅れて同じ足運びを行いながら、上半身を逆方向へひねる。 二人が互いの手首を一瞬だけ受け、その接点を使って素早く位置を交換する。停止しない。 6.0s–7.2s 位置交換直後、NOIRが手前になる。 NOIRが先行し、斜めシャッフル、ヒールトゥ、つま先スクレイプ、首から肩へのウェーブ。RENが半拍遅れて追う。 NOIRが片腕を大きく流し、RENがその腕の下を素早くくぐる。髪、布、チェーン、赤い布が強く揺れる。 7.2s–8.4s カメラが短く寄るが、膝下まで維持する。 RENがNOIRの肩付近へ手を滑らせ、NOIRがその手首を一瞬だけ受ける。二人は視線を合わせたまま、胸ヒット、肩ヒット、手首スナップを交互に返す。 REN、NOIR、REN、NOIRの順で半拍ごとにアクセントを交換する。 8.4s–9.6s 二人が接触を解き、反対方向へ同時に半回転。 RENは右回転、NOIRは左回転。回転終了と同時にクロスステップ、オープンステップ、指フリック。 ターンの軌道へ手描き回転線と短い残像。背景記号が二重の渦になる。 9.6s–10.8s カメラが自然に全身へ戻る。 二人が同じ方向を向き、RENが前、NOIRが後ろのシャドーダンス。RENが肩、胸、腰、手首を高速で連結し、NOIRが半拍遅れて追従する。 NOIRは最後の手首スナップだけ先回りし、RENの動きを追い越す。 10.8s–12.0s 先行役がNOIRへ切り替わる。 NOIRが高速クロスステップ、前後ステップ、片肘を外へ切る、胸ヒット、首スナップ。RENが半拍遅れて同じリズムを別方向へ返す。 二人の足元に交互の円形波紋。背景ポスターが一拍ごとに剥がれ、粒子へ変わる。 12.0s–13.2s 二人が向かい合う。 NOIRが右手を差し出し、RENが左手首で受ける。手を握り続けず、接点を使って二人が素早く逆方向へ一回転。 回転途中で前腕を組み、肩をかすめ、そのまま立ち位置を交換する。 13.2s–14.4s 二人が背中合わせになる。 NOIRが肩、胸、腰の順に高速で刻み、RENが半拍遅れて返す。次の2拍でRENが先行へ戻る。 背中を強く押し合わず、肩甲骨の接触を軸に小さく回転する。黒インクと白線が二人の輪郭に沿って走る。 14.4s–15.6s 二人が同時に反転し、正面へ戻る。 RENが高速ヒールトゥ、NOIRが逆方向のつま先タップ。腕は交差し、足はミラーになる。 RENがNOIRの前腕を一瞬引き、NOIRがその勢いを利用して身体を横へ流す。二人はすぐ離れる。 15.6s–16.8s カメラがわずかに低くなり、全身を強調。 二人が高速シャッフル、クロス、オープン、ヒールスイッチ。左右の足を素早く交換しながら、上半身は胸ヒットと肩ロールを続ける。 足元のグラフィティが連続して弾ける。動きを止めない。 16.8s–18.0s カメラが小さく押し込む。 RENが片手を帽子のつばへ触れ、すぐ外へフリック。NOIRが眼鏡の横へ指を近づけ、触れずに外へ流す。 二人が同時に首を切り、腰を逆方向へ流し、胸ヒットから手首スナップへ接続する。視線を短くカメラへ向ける。 18.0s–19.2s NOIRがRENの腕の下を高速でくぐる。 RENは腕を上げたまま静止せず、身体を同時にピボットさせる。NOIRが抜けた瞬間、二人が前後位置を交換。 ターンで銀とゴールドの粒子軌跡が交差する。 19.2s–20.4s 二人が斜め方向へ進みながら、ランニングマン変形、クロスステップ、肩ヒットを連続する。 RENが半拍先行、NOIRが半拍遅延。2拍後に役割が反転し、NOIRが先行する。 カメラは短く引き、二人の移動範囲と全身を維持する。 20.4s–21.6s 二人が前腕を組み、一瞬だけ互いに外側へ体重を預ける。 傾いた姿勢を保持しない。すぐ反動で中央へ戻り、肩をかすめながら左右へ抜ける。 戻る動きに胸ヒット、手首スナップ、指フリックを重ねる。円形VFXが二人の間で弾ける。 21.6s–22.8s 二人が並び、短い完全ユニゾン。 ヒールトゥ、クロスステップ、胸ヒット、肩ロール、首スナップ、両手首スナップを高速で連結する。 完全同期は約2拍だけ。後半はRENが半拍先行し、NOIRが逆方向へ動きを流す。 22.8s–24.0s NOIRが前、RENが後ろの縦配置。 NOIRが身体を斜めへ切り、片腕を顔の横から外へ流す。RENが後方から半拍遅れて同じ軌道を反対側へ返す。 二人が同時に半回転し、前後位置を入れ替える。背景の抽象図形が縦方向へ伸びる。 24.0s–25.2s RENが高速クロスステップからNOIRへ接近。 RENの片手がNOIRの肩を一瞬かすめ、NOIRはRENの腰付近の揺れる布へ触れず、軌道だけを追う。 二人は身体を近づけたまま肩、胸、腰を交互に刻み、次の拍ですぐ離れる。 25.2s–26.4s カメラが少し下がり、足元を含む全身。 二人が逆方向の高速シャッフル。つま先タップ、ヒールスイッチ、足の交差、オープンステップ。 上半身は止めず、肩ヒット、首スナップ、指フリックを同時に行う。床の反射へ青、赤、金の光が走る。 26.4s–27.6s 二人が再び向かい合い、手首を一瞬接続する。 RENがNOIRを引くのではなく、互いの回転力を交換する。RENが右回転、NOIRが左回転し、回転後に肩をかすめてすれ違う。 すれ違いながら両者がカメラへ短く視線を送る。 27.6s–28.8s 二人が同じ方向を向き、最後の高速ユニゾンへ入る。 前後ステップ、クロスステップ、胸ヒット、右肩、左肩、手首スナップ、指フリック、タイトな半回転。 最初の2拍は完全同期。続く動きはRENが半拍先行、最後はNOIRが先行して終盤へ繋ぐ。 28.8s–30.0s 停止しないフィニッシュ。 二人が前腕を一度組み、反対方向へ身体を流し、その反動で中央へ戻る。腕を解きながら高速クロスステップ、肩ヒット、胸ヒット、手首スナップ。 RENが先にカメラを見る。NOIRが半拍遅れて眼鏡越しに視線を向ける。 決めポーズで固まらない。二人が次のターンへ入り始め、髪、ジャケット、ネクタイ、チェーン、赤い布が大きく揺れ、カメラも軽く押し込んでいる途中で終了する。 手描きVFX 実写映像に2D手描きアニメーションを重ねた質感。 白線、黒インク線、ラフなブラシライン、スピード線、円、バツ、波線、星形、稲妻、擦れた筆跡、短い残像を使用する。線は少し揺れ、意図的なコマ落ち感を持つ。 VFXは毎拍同じものを出さない。足、肩、胸、手首、指、ターン、二人の接触へ別々に反応する。顔、手、脚、衣装のシルエットを隠さない。 Negative Prompt スローモーション、遅いダンス、長いタメ、静止、ポーズ保持、開始時の棒立ち、歩くだけ、単調な横揺れ、地味な足踏み、同じステップの反復、低重心を続ける、膝を曲げ続ける、床ダンス、しゃがみ込み、長い視線の演技、顔だけのアップ、接触したまま停止する、ゆっくりした回転、過剰なオービット、カメラ停止、サイドスライド、横追跡、カット、ジャンプカット、隠しカット、暗転、ショット切替、場面転換、別の場所、人物増殖、第三者、別人化、顔交換、衣装交換、帽子交換、眼鏡交換、髪型変更、衣装消失、アクセサリー消失、身体融合、手指崩壊、余分な手足、身体貫通、足滑り、宙に浮く、普通の背景、屋上、路地、廃ビル、倉庫、夜景、街並み、地味な衣装、普通の私服、読める文章、字幕、歌詞、ロゴ、透かし、白飛び、過剰なモーションブラー、ちらつき。
- Requiring 30 seconds to hold the intensity of a 15-second routine directly counters the model's tendency to slow long takes down.
- Pauses, walking and posing are banned by name, closing the usual escape routes.
- Accents are required every one to two beats on a named body part, which keeps the choreography reading as dance.
Moss-Covered Village J-Horror Run
A boy runs through a fog-drowned Japanese village past moss-covered humanoid figures, held in one waist-up tracking shot.
ジャパニーズホラーの空気感。彩度を落とした病的な緑と灰色のアンダートーンによるカラーグレーディング。腰から上のトラッキングショットのワンカット長回し。青いストライプのボタンダウンシャツにカーキのチノパンを着た少年が、霧に沈んだ静まり返った日本の田舎の集落の通りを走っている。少年の顔は静かな恐怖に震え、目には今にもこぼれそうな涙が光り、口は声にならない嗚咽をこらえるように薄く開いている。カメラはゆっくりとした意図的な手持ちの動きで少年に寄り添うように漂う。集落は不気味なほど静か。濃い白い霧が家々の間に低く垂れ込め、すべての音を吸い込んでいる。通りのあちこちに、苔・蔦・絡まった緑の葉で全身が覆われた人型の存在が、ゆっくりと硬直したゾンビのような歩き方で、濡れた路面に足を引きずりながら歩いている。その動きは機械的で不自然。一部は少年が通り過ぎると顔のない苔の頭をゆっくりと回し、別の個体は不気味な遅延動作で蔦の腕を伸ばす。音楽はなし、濡れた足音とかすかな水滴の音だけ。少年は通りの植物人間をすり抜け、木造家屋の間の狭い路地へ入る。カメラは薄暗い通路を追う。路地にも数体の植物人間が同じ遅いゾンビ歩きでのろのろと移動しており、苔むしたシルエットが薄暗い中で黒い木の壁と見分けがつかない。少年は脇をすり抜け、必死に日本家屋の引き戸を押し開けて中に入る。カメラは室内へ続く——薄暗い和風建築の内部が一瞬映る。板張りの廊下がまっすぐ奥へ伸び、両側の部屋は開いた襖の向こうに畳の間が見え、壁には黒カビのシミ、あらゆる表面に湿気が光り腐敗を暗示する。廊下や部屋の中を植物人間が同じ硬直したゾンビ歩きでゆっくりと移動している。苔の体がほぼ暗闇の中で蠢く。少年はすぐに奥の出口を見つける——廊下の突き当たりの木の戸。軋む板張りの廊下を駆け抜ける。廊下にいた植物人間がゆっくりと体を回し、少年が通り過ぎる際に苔の腕を伸ばす。少年は裏手の戸を引き開け、家の裏の灰色の曇天の下に広がる畑へとよろめき出る。カメラは地面近くまで下がり、ニンジンの葉や大根の葉の列の間から向こう側を覗く。背景に少年が畑を横切って走る姿が霧の中にぼんやり見える。長く居心地の悪い間。やがて手前の葉が震え始める——激しくではなく、ゆっくりと忍び寄るような震え。暗く湿った土の中から、実物と同じサイズの大根・ニンジン・カブが、腕や脚のような根の形をして音もなく地面から這い出してくる——どれも拳ひとつ分から前腕ほどの実際の野菜の大きさ。最初はゆっくりと現れ、青白い体から土がぼろぼろと崩れ落ち、やがて速度を上げて土の上をよちよちと歩き出す。囁きと叫びの間のような細く甲高いキーキー音を発する。畑のあらゆる畝から数百体が姿を現す。カメラがゆっくりと上がり少年を捉える。少年は立ち止まっている。足元を見下ろす。表情が困惑から純粋な恐怖へと変わる。小さな根菜たちが足元に群がり、何十本ものニンジン・白い大根・丸いカブが靴にしがみつきズボンの裾をよじ登る。少年は震えながら振り払おうとするが、四方八方からさらに押し寄せる——キーキー鳴く小さな野菜の潮流が黒い土の上を流れるように少年へ向かってくる。少年は膝をつく。カメラがゆっくりと安定した軌道で少年を中心に回り始める。Jホラー映画のような冷静な客観性をもって。根菜たちが細い鳴き声の合間の沈黙の中で積み重なっていく——胴体をよじ登り、腕をつかみ、肩と背中に群がる。少年の嗚咽が空っぽの畑に響く。少年は仰向けに倒れ込み、まだ弱々しく根菜を押し返そうとしている。カメラは急がない軌道で回り続け、根菜が層を成して少年を埋めていく——脚が消え、胸が覆われ、腕が飲み込まれる。叫びがくぐもり、やがて無音になる。青いストライプシャツの最後の一片が、数百体の小さな野菜が蠢く塚の下に消える。カメラが緩やかにやや高い位置へと上昇する——真俯瞰ではなく、軽いハイアングルで脈打つ根菜の塚を見下ろす。この視点から畑の全体が四方に広がる。あらゆる畝、あらゆる溝から、無数の小さな根菜——ニンジン、大根、カブ——が根の足で土から出てきて、中央の塚に向かって静かに途切れることなく行進を続けている。果てしない、音のない行列。音響：濡れた足音、水滴、木の軋み、かすかな風、遠い囁きのように層を成す細い甲高い鳴き声、土が静かに裂ける音、少年の叫びがくぐもった沈黙へと消えていく、土の上を根が這う静かなざわめき。
- A sickly green-grey grade is specified as the colour scheme, which carries the horror tone without any effects.
- Fog absorbing all sound is described as an audio property, so the silence is designed rather than absent.
- The creatures are given mechanical, stiff movement, which is far more unsettling than described monstrosity.
Blockbuster Pop Duet Music Video
A 30-second luxury pop duet MV: two consistent pop stars lip-sync through editorial sets while magazine-style typography integrates into the environment.
Create a premium 30-second cinematic pop music video in 16:9 landscape with blockbuster production quality. The video features one female pop superstar and one male pop singer with youthful, attractive faces, expressive eyes, natural skin texture, confident stage presence, and authentic chemistry. Both artists remain visually consistent throughout every shot. The female artist wears a crystal-embellished blush corset, oversized pastel pink faux-fur jacket, glossy satin cargo pants, platform sneakers, layered diamond jewelry, shimmering body chains, glamorous editorial makeup, luminous skin, glossy lips, and flowing textured hair. The male artist wears an oversized powder-blue embellished trench coat, shimmering silver knit top, relaxed ivory trousers, crystal sneakers, tinted luxury sunglasses, layered silver chains, rings, bracelets, and premium pop-star accessories. Their outfits naturally react to wind and movement. Both artists actively perform the song with perfect lip synchronization, realistic mouth movements, expressive facial expressions, confident body language, and emotional delivery. They frequently sing directly into the camera. During instrumental moments they naturally interact with each other through elegant movement and subtle choreography. Reserve full choreography only for the chorus with professional backup dancers. Blend luxury pop music, Vogue fashion editorials, beauty campaigns, Y2K magazine aesthetics, and world-tour concert visuals. Every frame should resemble a global luxury fashion campaign while remaining fully photorealistic. Use oversized editorial typography throughout the video with bold condensed fonts, magazine layouts, barcode graphics, registration marks, index numbers, halftone textures, paper overlays, handwritten notes, star icons, heart graphics, sparkles, waveform graphics, glossy gradients, and premium motion graphics. Typography should naturally integrate into architecture, LED screens, mirrors, glass, streets, reflections, and stage environments. Use uplifting pop phrases such as "FEEL THE LOVE", "STAY GOLDEN", "FOREVER YOUNG", "POP VIBES", "HEARTBEAT", "LIVE THE MOMENT", and "SHINE BRIGHT". Do not repeat the same layout twice. Visual quality should resemble ARRI Alexa 65 with Cooke Anamorphic lenses, IMAX-quality cinematography, HDR color science, cinematic lens flares, volumetric haze, premium beauty lighting, elegant camera movement, shallow depth of field, ultra-realistic skin texture, blockbuster VFX, and luxury commercial production. Scene 1 (0–5s) Inside a luxurious pastel studio featuring giant LED walls, glossy reflective floors, sculptural lighting, mirrors, floating curtains, soft haze, and elegant fashion set design. The female artist opens the song singing directly into the camera while the male artist joins naturally. Oversized kinetic typography and editorial graphics animate around them. Scene 2 (5–10s) Golden-hour rooftop overlooking a modern skyline with reflective glass architecture, designer furniture, and warm sunlight. The artists walk together while singing confidently. Editorial typography wraps around the skyline and architecture. Scene 3 (10–15s) Blue-hour luxury shopping district filled with designer boutiques, giant LED billboards, luxury cars, colorful signs, and cinematic reflections. The artists perform naturally while the camera circles around them. Typography integrates into billboards and digital displays. Scene 4 (15–20s) A spectacular sold-out concert arena featuring massive LED screens, lasers, pyrotechnics, confetti, smoke, moving spotlights, synchronized lighting, professional dancers, and thousands of cheering fans. The artists perform the chorus with energetic choreography and perfect lip-sync. Scene 5 (20–25s) A luxury penthouse at night overlooking a breathtaking skyline with floor-to-ceiling windows, infinity pool reflections, crystal chandeliers, designer interiors, modern art, and elegant ambient lighting. The artists perform together in an intimate yet glamorous atmosphere while editorial graphics subtly float around them. Scene 6 (25–30s) A surreal luxury stage floating above golden clouds at sunrise with mirror floors, cinematic fog, shimmering particles, elegant architecture, and breathtaking golden light. The artists perform the emotional final chorus as dramatic close-ups alternate with cinematic hero shots. Massive elegant typography, fireworks, editorial graphics, lens flares, and premium motion design create an unforgettable blockbuster finale before fading to black.
- Wardrobe for both artists is specified down to jewelry, so identity holds without any reference image.
- Choreography is rationed — full dance is reserved for the chorus — which stops the whole clip from becoming undirected movement.
- Typography is treated as production design that lives on LED screens, glass and streets, not as subtitles, so on-screen text feels intentional.
Rainstorm Watchtower Rescue
A four-shot rain rescue written as a full production spec — references, location map, per-shot FOV and distance, hard-cut times and physics notes.
SCENE CONTEXT A young Japanese man carries an exhausted young woman in his arms through the rain into an old wooden watchtower shelter. He lays her on a wooden bench, then removes his own coat and wraps it around her so she won't feel the cold, before moving to guard the door — staying alert until he finally rests too, a respectful distance kept throughout. Photorealistic, cinematic movie-scene quality, real Japanese actors, not anime/illustrated. ACTIVE REFERENCES <<<image_3>>>: young Japanese man, damp black hair, dark coat over tunic, protective carrying posture, real human skin texture. 100% matches reference. <<<image_1>>>: young Japanese woman, damp dark hair, kimono-style travel robes, eyes closed, limp and shivering in his arms. 100% matches reference. <<<image_2>>>: wooden Japanese watchtower interior. 100% matches reference, consistent across all shots. LOCATION MAP - Old sliding wooden door, ajar, rain/wind leaking through. - Narrow window slit, storm-grey light, occasional lightning flicker. - Paper lantern (chochin) hanging from a beam — main light source. - Rough wooden walls, old crates, straw mat in corner. - Worn wooden bench where she's laid down. - Puddle near door threshold, lantern reflection. FIRST FRAME He steps through the doorway carrying her, her head against his chest, both drenched, rain visible behind, lantern light on their faces. FORMAT MODE Four-shot sequence, HARD CUTs at 3.5s, 7.5s, 11.0s. Handheld only for carry shot. Photorealistic, natural skin/fabric physics. No subtitles, no music. OPTICS & CAMERA Shot 1 (carry): 50° FOV, 1.5–2m, gentle handheld follow as he enters. Shot 2 (lay down): 56° FOV, 1–1.3m, push-in as he lowers her onto the bench, faint shiver visible. Shot 3 (coat cover): 60° FOV, 2m, three-quarter angle as he removes his coat and wraps it around her, tucking the edges in. Shot 4 (guard, then sleep): 63° FOV, low near door, crane-up to high three-quarter — him now coatless at the door, staying alert, finally closing his eyes to sleep, her warm and undisturbed on the bench. ACTION TIMING 0–3.5s: he carries her in through the rain, her head lolling against his chest. 3.5s CUT. 3.5–7.5s: he lays her on the bench, a small shiver crossing her. 7.5s CUT. 7.5–11.0s: he takes off his coat, wraps it snugly around her. 11.0s CUT. 11.0–15.0s: coatless, he sits guard at the door, alert despite the cold, then eyes close as he finally falls asleep — she stays warm, a clear gap kept between them. PHYSICS Real dead-weight in the carry, wet hair swaying. Coat drapes and settles naturally around her. His bare tunic shows subtle cold response — slight shoulder hunch — through the guard shot. LIGHTING Cinematic low-key, warm lantern glow vs cool blue-grey storm light through the window/door. Faces stay readable, natural film grain, never flat or CG-looking. AUDIO Rain, footsteps, effortful breathing (shot 1); wood creak, faint shiver (shot 2); coat rustle (shot 3); quiet exhale, rain softening, steady breathing (shot 4). No dialogue, no music. POSITIVE LOCKS Man matches <<<image_3>>>, woman matches <<<image_1>>> exactly — photorealistic, not anime. Shelter matches <<<image_2>>> exactly across all shots. He gives her his coat so she won't feel cold, leaving himself in just his tunic. He keeps guard at the door, only sleeping in the final shot, a respectful distance maintained throughout.
- A location map lists every prop and light source before the action, so all four shots stay in one coherent space.
- Each shot specifies FOV, camera distance and one blocking task; nothing competes inside a cut.
- Physics notes (dead weight, wet hair, coat draping) target the exact details that break believability in carried-body shots.
Nine-Panel Storyboard Desert Sequence
One reference image holds a nine-panel storyboard; the prompt renders all nine panels as a seamless 30-second desert caravan sequence in strict order.
Use @[image1] as storyboard reference for cinematic sequence. use as first shot 01 A 30-second majestic cinematic sequence transitioning smoothly through all 9 storyboard panels in strict chronological order. Visual style: luxury travel commercial, photorealistic 8K, hyper-detailed sand textures, rich golden hour lighting, volumetric atmosphere, silk-like fabric physics. CRITICAL: Absolutely NO frames, borders, film strips, numbers, UI, or text. Render as seamless full-screen cinematic shots only. Ignore grid layout completely. Maintain 100% fidelity to the composition, color palette, and textures of the reference panels. Shot 1 (0-3.3s): Panel 1. Wide cinematic shot. A caravan of camels walks in silhouette against a massive setting sun. Deep shadows and golden rim light. Camera pans slowly right, following the footprints in the sand. Shot 2 (3.3-6.6s): Panel 2. Low-angle tracking shot. Camels drinking from a crystal-clear oasis. Palm trees sway gently in the breeze. The water reflects the golden sky with realistic ripples. Shot 3 (6.6-10.0s): Panel 3. Drone shot rising. A lone rider guides a camel up the steep ridge of a massive sand dune. The sun is a giant glowing orb behind them. Sand grains shift realistically under hooves. Shot 4 (10.0-13.3s): Panel 4. Long lens shot. A majestic desert city with minarets shimmers in the heat haze across a vast sandy plain. The caravan moves slowly towards the mirage. Atmospheric perspective is deep and rich. Shot 5 (13.3-16.6s): Panel 5. Tracking shot. The caravan passes through ancient stone arches and ruins. Sunlight streams through the columns, highlighting the weathered stone texture and dust particles in the air. Shot 6 (16.6-20.0s): Panel 6. Dynamic action. A powerful sandstorm swirls around the caravan. The wind whips the sand and cloaks dramatically. High contrast, dramatic lighting, raw power of nature. Shot 7 (20.0-23.3s): Panel 7. Night scene. A tranquil camp under a starry sky with the Milky Way visible. A warm campfire crackles in the center, illuminating the faces of travelers and the canvas of tents. Shot 8 (23.3-26.6s): Panel 8. Wide establishing shot. The caravan moves across endless rolling dunes at sunset. The wind creates intricate patterns on the sand ridges. The light is warm, soft, and inviting. Shot 9 (26.6-30.0s): Panel 9. Grand Finale. The caravan arrives at the gates of a magnificent city with domes and towers. The sun sets perfectly behind the architecture. Camera slowly zooms out to reveal the scale of the destination. ZERO TEXT. Style reinforcement: seamless transitions, cinematic camera movement, rich color grading, consistent golden aesthetic, high-end commercial quality, NO text, NO grid, NO numbers, photorealistic details.
- A single grid image carries the whole shot plan, and the prompt tells the model to ignore the grid layout — a clever division of labor.
- The “absolutely no frames, borders, film strips” ban attacks the predictable failure of grid references leaking into the output.
- Each panel still gets its own camera instruction, so the storyboard governs composition while the text governs motion.
Rainforest Flood Escape on a Giant Lynx
A compact escalating event chain: a warning, a sprint through the downpour, a giant blue lynx mount, and a cliff-top view of the flood swallowing the jungle.
A woman tells the villagers: "Torrential waters are approaching; the ground is shaking beneath your feet." Run toward the mountains. She sprints through the tropical rainforest amidst a torrential downpour. Handheld camera shot; chaos. A torrent of water chases the woman, tearing through the jungle; rapid motion blur. A massive lynx—muscular, with long blue fur and long ears—runs through the tropical rainforest in the pouring rain. The woman mounts the giant lynx and rides it; the beast races toward the mountains, rapidly climbing to the summit while leaping great distances with the woman on its back. A shot of the blonde woman atop the giant lynx—with its long blue fur and honey-colored eyes—perched high on a cliff overlooking the rainforest; below, a massive flood rages, with giant torrents of water submerging the jungle, sweeping away exotic villages and engulfing elephants in the deluge. They gaze out at the scene from the top of the cliff. photorealistic cinematic scene of high-octane action.
- Every sentence advances the causal chain — warning, flight, rescue creature, escape, aftermath — with no static description.
- The lynx gets exactly the details that matter at speed: size, blue fur, long ears, honey eyes.
- Ending on a wide aftermath vista converts chaos into a clean visual resolution.
K-pop Trio Laughing Stage Moment
Three idols on an LED-lit stage keep dancing while breaking into synchronized laughter, ending on double peace signs to the camera.
A vibrant K-pop stage performance under bright purple and pink LED lights. Three young East Asian women idols with long dark hair stand in a line on stage, wearing headset microphones and stylish crop tops. Characters and outfits: Left idol: lime-green sleeveless top with white “BOYS LIE SPORT” text and heart logo. Center idol: baby-pink spaghetti-strap crop top with white piping. Right idol: navy-and-green horizontal striped collared crop top. Sequence — approximately 17 seconds: 0–2s: The three idols begin by dancing lightly and naturally in sync to the beat. The center idol flips her long hair and turns slightly while dancing. The right idol dances with a playful expression. Do not have them cover their faces yet. Soft stage lighting and large LED screens show a big red “5” and heart graphics in the background. 2–6s: While continuing their dance movement, all three suddenly bring both hands up to cover their mouths, reacting with genuine surprise and laughter. Their shoulders shake as they giggle and they gently bounce in place. The center idol laughs hardest, with her long hair naturally swaying. 6–12s: They continue the synchronized cover-mouth-and-laugh motion while still subtly dancing to the beat. Keep their bodies moving naturally rather than freezing in place. Their expressions are joyful, playful, and genuinely amused. Medium camera framing captures all three idols clearly. 12–15s: The dancing continues at 12 seconds as they smoothly transition from covering their mouths into making double peace signs with both hands raised near their faces. They keep moving rhythmically while smiling and laughing. The center idol briefly turns and then faces forward again. 15–17s: Final pose while the dance energy continues subtly — all three hold double peace signs near their faces, beaming directly at the camera with bright, cheerful expressions. Soft stage haze and colorful LED lighting create a high-energy yet adorable K-pop concert atmosphere. Visual style: high-quality live concert footage, sharp details, natural skin texture, realistic facial expressions, dynamic but soft purple-and-pink stage lighting, subtle handheld camera shake for realism, natural hair movement, believable body motion, polished K-pop performance cinematography, cute, energetic, wholesome atmosphere. Important motion requirements: The idols must dance first before putting their hands on their faces. Do not start with their hands covering their mouths. The dancing continues throughout the sequence, including after the 12-second mark. No frozen poses before the final moment. No text overlays.
- The prompt sequences emotion like choreography — dance first, then the covered-mouth laugh, then peace signs — with explicit ordering rules.
- “Keep their bodies moving rather than freezing” prevents the classic failure where a reaction beat stops all motion.
- Each idol gets one outfit line, enough to keep three characters distinct without reference images.
Looking for the Seedance 2.5 API?
Model page with per-second pricing, five generation modes, and integration docs.
Seedance 2.5 prompt guide
How to Prompt Seedance 2.5
Start with one clear role for every reference, direct longer clips in timed beats, and change one variable at a time when a result misses the brief.
A practical Seedance 2.5 prompt structure
Reference roles → format and duration → timed action beats → camera and audio → must-keep constraints
01
How to structure a 30-second Seedance 2.5 prompt
Write the clip as timed beats — [0–5s] setup, [5–20s] action, [20–30s] payoff — and give each beat one main event and one camera goal. End every beat with its exit state (position, facing, what is in hand) so the next beat continues from it instead of teleporting.
02
How to assign reference images in Seedance 2.5
Name each reference and state its job before the action begins: character identity, product appearance, location, motion, style, or voice. A request carries up to 30 images, 10 videos, and 10 audio clips — reuse the same labeled pack across every shot of a project so subjects stay consistent.
03
One named camera move per shot
“Cinematic” tells the model nothing — name the exact move: slow push-in, pull-back, side tracking, handheld walking, crane down. Keep one move per shot; when you need two, split them across timestamps and let the model cut between them.
04
Always write the audio line
Seedance 2.5 generates audio together with the picture, so an unwritten audio line is a decision you hand to the model. State dialogue, ambience, and music — even “ambient sound only, no music” is direction.
05
Constraints beat vague negatives
There is no separate negative-prompt field — write bans as one short constraints line: no readable text, no logos, no extra characters, preserve identity. “No readable text” earns its place in almost every prompt; a long ban list buries the subject.
06
How to fix one failed time segment
Change the instruction inside the failed time range first, then rerun the prompt — or send the clip through the video-edit mode and rewrite only that range. Keep the beats that already worked intact instead of rewriting the whole sequence.
07
Test the structure at 480p before the 720p final
Draft at 480p to validate composition, timing, and reference roles — and test a 5–10 second opening before committing to full length. When a draft hits, extend it with the video-extend mode instead of regenerating longer takes from scratch.
Upscale clips to 4K with Topaz Video Upscale →08
How many references should you use?
Use only references with a clear job. More inputs are not automatically better: every extra asset adds another constraint the model must reconcile. Add a reference when text alone cannot reliably preserve something important.
09
When should you split a long prompt into shorter shots?
If a long prompt keeps losing continuity, break it into shorter shots and stitch them later. This gives you more control over blocking, pacing, and retries while keeping the full one-take approach for ideas that remain stable.
Fix weak generations
Change the instruction that failed.
Identity driftsAssign each reference one explicit role before describing the scene.
Story loses structureDivide the prompt into timed beats with one job per segment.
Subject teleports between beatsWrite each beat’s exit state — position, facing, held objects — and start the next beat from it.
Fast action gets chaoticLock positions, facing direction, momentum, and what carries across cuts.
Dialogue feels detachedKeep lines short and place sound cues inside the matching timed beat.
Only a few seconds are wrongEdit that time range with the video-edit mode instead of rerolling the whole clip.
Fit check
Choose 2.5 for the job, not the version number.
Choose Seedance 2.5
- ✓ 30-second structure with timed beats
- ✓ Multi-reference control with assigned roles
- ✓ Picture, dialogue, and sound directed together
- ✓ Lower project cost when rerolls are the real expense
Choose Seedance 2.0
Shorter, simpler shots where lower generation cost matters more than orchestration.
Compare another model
When your priority is a specific visual style, speed tier, or capability outside this workflow.
FAQ
Seedance 2.5 Prompt FAQ
What makes a good Seedance 2.5 prompt?
A strong prompt separates the story beat, subject action, camera path, reference roles, audio, and constraints. Use concrete timing and movement language instead of stacking vague style adjectives.
How do I write a 30-second Seedance 2.5 prompt?
Split the video into four to six timestamped beats. Give each beat one main action, one camera instruction, and any required dialogue or sound cue, then define the final payoff.
How should I describe reference images, video, and audio?
Name every reference and give it one job, such as character identity, product appearance, motion path, visual style, dialogue voice, or ambience. Do not ask one reference to control unrelated details.
Can Seedance 2.5 prompts control dialogue and native audio?
The examples show useful patterns for assigning lines to speakers, separating dialogue from music, describing ambience, and preventing voice crossover or unwanted subtitles.
Do Seedance 2.0 prompts work in Seedance 2.5?
Yes, the subject, action, camera, and style instructions are still useful. For Seedance 2.5, adapt longer ideas into timed beats, assign explicit roles to reference assets, separate dialogue from music and ambience, and add constraints for anything that must remain consistent.
Where do these prompt examples come from?
The gallery separates official showcase clips from sourced community examples and keeps author attribution on each community card. Source URLs remain available for internal verification, and these previews are not presented as EvoLink API benchmarks.
Can I generate with these prompts on EvoLink?
Yes. Choose Use on any example — it carries the full prompt into the Seedance video generator, where you can adjust the prompt and settings before generating.
Keep going
Continue your Seedance workflow
Seedance 2.5 model and pricingCompare model modes, current pricing, production limits, and route performance.Seedance video generatorExplore the broader Seedance generation workflow and model choices.Seedance 2.5 vs Seedance 2.0Compare output control, references, duration, audio, and cost before choosing a route.Hailuo 3 vs Seedance 2.5Compare commercial-ad editing, long-form control, audio, and current production fit.Seedance 2.0 PromptsUse the lower-cost 2.0 prompt library when the workflow does not need 2.5 capabilities.Seedance 2.5 API docsExact request fields, model IDs, and production integration details.