Kling 3.0 动作控制 API
通过参考视频驱动角色图像动画,支持朝向控制、原声保留和异步 API 交付,满足生产级工作流需求。
- 起始价格 $0.1134/s
- 720p / 1080p
- 输入: 图像 + 视频
- 最长 10s / 30s

Reference video motion, image character guidance, and async delivery in one production-ready route.
No sample available
Motion source video (MP4/MOV, 340-3850px per side, 3-30s, max 100MB)
Click to upload or drag and drop
Supported formats: MP4, MOV
Maximum file size: 100MB; Maximum files: 1
Character image to animate (JPG/PNG, max 10MB)
Click to upload or drag and drop
Supported formats: JPG, JPEG, PNG
Maximum file size: 10MB; Maximum files: 1
Click Generate to see preview
History
最多保留20条0 运行中 · 0 已完成
Billing Rules
- •Price shown is per second
- •Billed by output video duration, rounded to nearest integer
- •Duration depends on reference video (max 10s for image orientation, 30s for video orientation)
- •Total = price/second × actual duration
Pricing
| Model | Mode | Quality | Price |
|---|---|---|---|
| Kling 3.0 Motion Control | Motion Control | 720p | Popular $0.1134/ second(8.1648 Credits) |
| Kling 3.0 Motion Control | Motion Control | 1080p | $0.1512/ second(10.88368 Credits) |
If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.
动作控制 API 可以构建什么应用?
虚拟形象和角色动画:从参考视频驱动
将静态角色图像通过参考表演视频驱动成动画,无需手动绑定骨骼或逐帧编辑。这种工作流适用于创作者工具、虚拟形象、短视频内容和角色驱动的视频制作,特别是需要自然人物动作的场景。

舞蹈、手势和表演迁移:适用于社交内容
将舞蹈动作、手势和身体表演从一个视频迁移到不同角色,用于社交媒体制作、营销素材和创作者工作流。团队可以将单个动作源转换为多个角色主导的输出,加快营销活动的迭代速度。

参考驱动的动作工作流:支持朝向控制
控制生成的角色是跟随源图像的方向还是参考视频的方向,然后根据预算和制作需求选择 720p 或 1080p 输出。这为开发者提供了比通用图像转视频生成更结构化的动作控制管道。

为什么团队选择动作控制 API
Kling 3.0 动作控制为团队提供了一种更可控的方式,将真实表演素材转换为角色动画,具有可预测的按秒定价和生产就绪的 API 工作流。
比通用视频生成更可控
动作控制不是让模型从零开始创造动作,而是使用参考表演视频作为动作源。这使得输出行为更容易控制,特别适合角色驱动的工作流。
无需手动绑定骨骼,加快制作速度
团队可以将静态图像加上动作片段转换为可用的动画输出,无需构建传统的动画管道。这降低了原型、营销素材和创作者工具的设置门槛。
可预测的 API 定价,适合重复工作流
按秒计费、720p 和 1080p 模式以及明确的时长限制,让成本估算更容易。这对批量任务、用户生成内容工作流和自动化内容管道很重要。
如何集成动作控制 API
从参考输入到交付动画的三个实用步骤。
准备清晰的角色图像和动作源视频
上传目标角色的参考图像和包含要迁移表演的参考视频。清晰的身体可见度和稳定的源动作可以提高输出一致性。
提交带动作设置的异步生成请求
将图像、视频、画质模式和朝向参数发送到 API。任务异步运行,更容易集成到生产管道、队列系统和自动化工作流中。
轮询任务状态、审查输出并迭代
检查任务状态直到结果就绪,然后审查生成的片段并在需要时优化输入。这种迭代循环适用于创作者产品、内部工具和可重复的视频工作流。
动作控制 API 核心能力
视频驱动的角色动画
动作迁移
从参考视频中提取动作并应用到参考图像中的角色,生成自然的动画效果,无需手动操作。
角色朝向控制
选择输出角色面朝的方向——与参考图像一致或与参考视频一致,实现精确控制。
主体元素支持
使用通过 Kling 主体创建功能创建的自定义主体元素,在不同生成中保持角色外观一致。
原声保留
可选择保留参考视频中的原始音频到生成的输出中。
按秒计费
仅按实际生成时长付费。按秒计费,实际时长向上取整到最近的整数秒。
720p 和 1080p 画质
在标准 720p(std)和高清 1080p(pro)输出之间选择,为特定用例平衡质量和成本。
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 Motion Control Video
Kling 3.0 Motion Control (kling-v3-motion-control) transfers human motion from a reference video onto a character in a reference image.
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
- Both reference image and reference video are required.
- Max duration: 10s (image orientation) or 30s (video orientation).
- Billed by actual generated duration, rounded to nearest second.
- Pricing: 720p = 1.0x base, 1080p = 1.333x base.
Request Parameters
modelstringRequiredDefault: kling-v3-motion-controlMotion control model name.
kling-v3-motion-controlimage_urlsstring | string[]RequiredReference image URL(s). The character in this image will be animated with the motion from the reference video.
Notes
- Formats: JPG, JPEG, PNG
- Max size: 10MB
- Dimensions: 300px-65536px per side
- Aspect ratio: 1:2.5 to 2.5:1
- Character should show clear upper body or full body
- Avoid extreme orientations (e.g., upside down, lying flat)
https://example.com/character.pngvideo_urlsstring | string[]RequiredReference video URL(s). The motion in this video will be transferred to the character in the reference image.
Notes
- Formats: MP4, MOV
- Max size: 100MB
- Dimensions: 340px-3850px per side
- Duration: 3s minimum
- Max 10s (image orientation) or 30s (video orientation)
- Recommend single-person video with clear, steady motion
- Avoid camera cuts, fast motion, or scene transitions
https://example.com/dance.mp4promptstringOptionalOptional text prompt to add elements or camera effects to the generated video.
Notes
- Max 2500 characters
- Can describe clothing, scene additions, or camera movements
A girl wearing a gray loose T-shirt and denim shortsqualitystringRequiredVideo output quality. Affects billing multiplier.
| Value | Description |
|---|---|
| 720p | Standard quality (1.0x base price) |
| 1080p | High quality (1.333x base price) |
720pmodel_params.character_orientationstringRequiredControls the facing direction of the generated character.
| Value | Description |
|---|---|
| image | Character faces same as reference image (max 10s) |
| video | Character faces same as reference video (max 30s) |
Notes
- When using element_list, only 'video' orientation is supported
imagemodel_params.keep_soundbooleanOptionalDefault: trueWhether to keep the original audio from the reference video.
Notes
- true = keep original sound, false = mute
truemodel_params.element_listarrayOptionalSubject element references for consistent character appearance.
Notes
- Format: [{element_id: string}]
- Max 1 element
- Only video-created elements supported (reference_type=video_refer)
- When used, character_orientation must be 'video'
[{"element_id": "12345"}]model_params.watermark_infoobjectOptionalWatermark configuration for the generated video.
Notes
- Format: {enabled: boolean}
{"enabled": false}callback_urlstringOptionalHTTPS callback address after task completion.
Notes
- Triggered on completion, failure, or cancellation
- HTTPS only, no internal IPs
- Max length: 2048 chars
- Timeout: 10s, Max 3 retries
https://your-domain.com/webhooks/video-task-completed