Kling O1 API
Kling O1 video generation model with image-to-video, video editing, and fast video editing variants. Supports 3-20 second videos with reference images for style-guided generation.
Upload images to generate video
A cinematic transformation video. Start with the model standing in a clean white photography studio, wearing a simple nude-tone fitting outfit. The camera is steady, 9:16 vertical, natural soft light. The model makes very subtle natural movements such as blinking or shifting her weight. Then, the environment begins to slowly transform. Soft pastel mist fades in behind her. Large pink flowers begin to appear and grow around her in a magical, elegant way. The grass and dreamy atmosphere gradually form. The lighting becomes more cinematic and soft. Next, her outfit transforms from the simple fitting outfit into the final fantasy couture outfit shown in the reference: layered pink tulle dress, fluffy textured jacket, mint-green thigh-high stockings, and heels. The transformation must be smooth, elegant, and high-end. As the scene completes, the final environment fully resembles the dreamy floral fantasy world from the reference image. Extremely large pink flowers, lush green textures, soft cloudy sky. The model stands confidently in the completed scene and makes light natural movements, such as a gentle head turn or slight breathing motion. Ultra high-end, fashion commercial style. Final 2 seconds: the completed big scene, subtle motion in flowers like a gentle breeze, and the model holding a graceful pose.
Upload reference images
Click to upload or drag and drop
Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 10
History
最多保留20条0 运行中 · 0 已完成
面向统一视频生成与编辑的 Kling O1 API
使用 Kling O1 构建现代视频工作流。使用一个 API 从提示词创建新片段,精修现有素材,并使营销、社交内容和电商输出的角色和场景保持一致。

利用 Kling O1 API 可以构建什么?
为什么团队选择 Kling O1
Kling O1 强调统一的创作与编辑,并在角色和场景间保持一致性,从而减少返工并使创意流水线可预测。
统一的多模态工作流
文本、图像、视频和主体输入共存于一个模型中。
一致性优先的输出
在不同片段间保持可识别的角色和场景。
注重生产的定位
专为电影、社交、广告和电商工作流打造。
如何集成 Kling O1 API
从输入到生产就绪视频的简单流程。
选择输入与模式
根据您的工作流和期望的输出类型,选择文本、图像、视频或主体输入。
提交生成任务
发送带有指令和任何参考的请求,然后跟踪任务直到结果就绪。
评审与迭代
下载结果,比较变体,并复用相同的结构进行快速迭代。
Kling O1 API 核心能力
单一模型中的统一视频创作与编辑
统一的多模态引擎
Kling O1 作为一个统一的多模态模型推出,在单一系统中结合了生成和编辑。这允许团队在处理同一工作流中的新片段创建和编辑时保持单一集成。
文本、图像、视频和主体输入
公开描述强调 Kling O1 支持文本、图像、视频和主体输入。这为创作者提供了更多控制输出的方式,并在需要一致结果时减少了猜测。
角色和场景的一致性
Kling O1 旨在解决 AI 视频生成中的一致性挑战。这有助于团队在多个片段中保持角色身份、道具和场景细节的对齐。
生成加编辑工作流
Kling O1 将生成和编辑任务带入同一个引擎,而不是切换工具。这对于需要创建然后精修且不破坏连贯性的营销团队非常有用。
商业内容用例
该模型被描述为适用于电影、电视、社交媒体、广告和电商工作流。这使其成为大规模构建内容的团队的实用选择。
多模态视觉语言
Kling O1 基于多模态视觉语言框架构建。这有助于它解释文本和视觉参考中的意图,使输出更紧密地符合创意方向。
常见问题
Everything you need to know about the product and billing.
API Reference
Select endpoint
Authentication
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/videos/generationsCreate Video
Kling O1 Image to Video (kling-o1-image-to-video) model transforms static images into dynamic videos.
Asynchronous processing mode, use the returned task ID to query status.
Generated video links are valid for 24 hours, please save them promptly.
Important Notes
- At least one input image is required for image-to-video generation.
- Maximum 2 images per request.
Request Parameters
modelstringRequiredDefault: kling-o1-image-to-videoVideo generation model name.
kling-o1-image-to-videopromptstringRequiredPrompt describing what kind of motion and video to generate.
Notes
- Limited to 2000 tokens
A gentle breeze moves through the scene, creating subtle motion and life.image_urlsarrayRequiredInput image URL list for image-to-video generation.
Notes
- At least 1 image required
- Max 2 images per request
- Max size: 10MB per image
- Formats: .jpg, .jpeg, .png, .webp
- URLs must be directly viewable by the server
["http://example.com/image1.jpg", "http://example.com/image2.jpg"]aspect_ratiostringOptionalDefault: 16:9Video aspect ratio.
| Value | Description |
|---|---|
| 16:9 | Landscape video |
| 9:16 | Portrait video |
| 1:1 | Square video |
'16:9'durationintegerOptionalDefault: 5Specifies the generated video duration in seconds.
| Value | Description |
|---|---|
| 5 | 5 seconds duration (Base price) |
| 10 | 10 seconds duration (2x price) |
Notes
- Billing is based on duration: 8.064 credits per second
5callback_urlstringOptionalHTTPS callback address after task completion.
Notes
- Triggered on completion, failure, or cancellation
- Sent after billing confirmation
- HTTPS only, no internal IPs
- Max length: 2048 chars
- Timeout: 10s, Max 3 retries
https://your-domain.com/webhooks/video-task-completed

