> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Kling V3.0 Motion Control

The Kling V3.0 Motion Control tool can extract motion trajectories from a reference video and apply them to a reference image to generate a video while preserving subject consistency. It supports Standard and Pro modes, with billing by the second.

<Tip>
  This is an **asynchronous** API and only returns the task\_id of the asynchronous task. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated result.
</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API key}}.
</ParamField>

## Request Body

<ParamField body="image" type="string" required={true}>
  Reference image URL or base64-encoded image; supports .jpg, .jpeg, .png.
  The image file size must not exceed 10MB; both width and height must be >= 300px; the aspect ratio must be between 1:2.5 and 2.5:1.
</ParamField>

<ParamField body="video" type="string" required={true}>
  Reference motion video URL; supports .mp4, .mov.
  The video file size must not exceed 10MB; both width and height must be >= 300px; duration must be 3-30 seconds.
</ParamField>

<ParamField body="prompt" type="string">
  Positive prompt describing the scene, style, lighting, etc.; length must not exceed 2500 characters.

  Length limit: 0 - 2500
</ParamField>

<ParamField body="model_name" type="string" required={true} default="kling-v3-0-std">
  Model name. kling-v3-0-std: Standard mode, cost-effective; kling-v3-0-pro: Pro mode, better video quality.

  Available values: `kling-v3-0-std`, `kling-v3-0-pro`
</ParamField>

<ParamField body="negative_prompt" type="string">
  Negative prompt describing elements to avoid in the generated video; length must not exceed 2500 characters.

  Length limit: 0 - 2500
</ParamField>

<ParamField body="keep_original_sound" type="boolean" default={true}>
  Whether to keep the original audio from the reference video.
</ParamField>

<ParamField body="character_orientation" type="string" required={true}>
  Output frame mode:

  * image: Prioritizes the character pose and composition of the reference image, transferring the motion to the character in the image (outputs 5 seconds)
  * video: Prioritizes the character pose and composition of the reference video, applying the motion in the video to the character in the image (output duration matches the reference video, up to 30 seconds)

  Available values: `image`, `video`
</ParamField>

## Response Information

<ResponseField name="task_id" type="string" required={true}>
  Use task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated output.
</ResponseField>