> ## Documentation Index > Fetch the complete documentation index at: https://docs.imini.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling v3 Motion Control > Kling 3.0 motion control — use a character from a reference image and replicate motion from a reference video ## OpenAPI ````yaml /en/openapi/videos/kling-v3-motion-control.yaml POST /v1/videos/generate openapi: 3.1.0 info: title: Kling v3 Motion Control version: '1.0' description: >- Kling 3.0 motion-control model. Uses the character from a reference image as the subject and replicates the motion from a reference video. servers: - url: https://openapi.imini.ai/imini/router security: - ApiKeyAuth: [] paths: /v1/videos/generate: post: summary: Kling v3 Motion Control description: > Submit an asynchronous video generation task. You will need to poll the query endpoint to retrieve the result. > Model ID: `kling/kling-v3-motion-control` · Underlying: Kling 3.0 Motion Control Provide the subject (character / background / style) via `reference_images`, and the motion source via `reference_videos`. The character in the generated video will replicate the motion from the reference video. operationId: generateKlingV3MotionControl requestBody: required: true content: application/json: schema: type: object required: - model properties: model: type: string description: Fixed value `kling/kling-v3-motion-control`. prompt: type: string description: > The prompt, which may contain both positive and negative descriptions. Up to **2500** characters. example: A dancer performs graceful movements in a sunlit studio resolution: type: string description: Output resolution. Defaults to `720P`. default: 720P enum: - 720P - 1080P reference_images: type: array description: > Reference image. **Only 1 image is supported.** The character, background, and other elements in the generated video are driven by this image. **Content requirements**: - The character proportions should match the motion in the reference video — avoid driving a half-body character with full-body motion; - The character must clearly expose the full upper body or full body, including limbs and head, without occlusion; - Avoid extreme orientations (e.g. inverted, lying flat); the character should occupy a reasonable portion of the frame; - Both realistic and stylized characters are supported (humans / humanoid animals / some pure animals / some characters with humanoid limb proportions). **Image requirements**: - Formats: `jpg` / `jpeg` / `png`; - Size ≤ **10 MB**; - Dimensions: **300px – 65536px**; - Aspect ratio between `1:2.5` and `2.5:1`. maxItems: 1 items: type: object required: - url properties: url: type: string description: > Image address, in one of two forms: **1)** A publicly accessible URL (`http://` or `https://`); **2)** A Data URI base64 encoding (starting with `data:image/`). reference_videos: type: array description: > Reference video. **Only 1 clip is supported.** The character's motion in the generated video will match this video. **Content requirements**: - The character must clearly expose the full upper body or full body, including limbs and head, without occlusion; - We recommend a single-person video; if multiple people appear, the character occupying the largest portion of the frame is used; - Real-person motion is preferred; some stylized characters with humanoid limb proportions are also supported; - The video should be a single continuous shot with the character visible throughout — avoid cuts or camera moves (otherwise the clip will be cropped); - Avoid overly fast motion; steadier motion produces better results. **Video requirements**: - Formats: `MP4` / `MOV`; - Size ≤ **100 MB**; - Dimensions (both width and height must fall within): **340px – 3850px**; - Duration ≥ **3s**; the upper bound depends on `extra_params.character_orientation`: - `video`: **≤ 30s**; - `image`: **≤ 10s**. - Publicly accessible URL only; base64 is not supported. > For high-difficulty or fast motion, the model may only extract a usable subset of the motion (a minimum of **3s** of continuous usable motion is required). The generated result may be shorter than the uploaded clip. maxItems: 1 items: type: object required: - url properties: url: type: string description: >- Publicly accessible video URL. base64 is not supported. generate_audio: type: boolean description: Whether to generate audio. Defaults to `false`. default: false extra_params: type: object description: Extension parameters. required: - character_orientation properties: character_orientation: type: string description: > **Required.** Source for the orientation of the character in the generated video. - `image` — follow the orientation from the reference image; the reference video duration must be ≤ **10s**; - `video` — follow the orientation from the reference video; the reference video duration must be ≤ **30s**. > When using subject references (`<<>>`), only `video` is currently supported (orientation from the reference video). enum: - image - video additionalProperties: true examples: Motion Control (follow video orientation): summary: Motion Control (follow video orientation) value: model: kling/kling-v3-motion-control prompt: A dancer performs graceful movements in a sunlit studio reference_images: - url: https://example.com/character.jpg reference_videos: - url: https://example.com/motion-source.mp4 resolution: 720P generate_audio: false extra_params: character_orientation: video Motion Control (follow image orientation): summary: Motion Control (follow image orientation) value: model: kling/kling-v3-motion-control prompt: >- A stylized character mimics the reference motion in a cinematic scene reference_images: - url: https://example.com/character.jpg reference_videos: - url: https://example.com/motion-source-10s.mp4 resolution: 1080P extra_params: character_orientation: image responses: '200': description: Submitted successfully (asynchronous mode) content: application/json: schema: type: object properties: task_id: type: string description: Unique task ID, used for subsequent polling example: task_2042864638838083584 model: type: string description: The model ID used for this task example: kling/kling-v3-motion-control created_at: type: string description: Task creation time (ISO 8601) example: '2026-04-21T07:17:39.146Z' request_id: type: string description: Unique request ID example: 291a4117-9df8-4349-aee1-bdf8ffcacb9a '400': description: Validation Error (e.g. invalid parameter, invalid prompt) content: application/json: schema: type: object properties: error: type: object properties: code: type: string description: Error code example: INVALID_PARAMETER message: type: string description: Error message details example: >- reference_videos duration must not exceed 10 seconds when character_orientation is "image" status: type: integer description: HTTP status code example: 400 request_id: type: string description: Unique request identifier example: req_abc123 security: - ApiKeyAuth: [] components: securitySchemes: ApiKeyAuth: type: http scheme: bearer bearerFormat: API Key description: > Pass `Authorization: Bearer ` in the request header. Go to the [API Keys management page](https://imini.ai/api-keys) to create and manage API Keys. ````