Kling AI

Kling Motion Control

Motion Control is not a text-only generator: it requires both a character image and a motion video. The image supplies appearance and scene elements, the video supplies the action, and an optional prompt can clarify additions or motion intent; versions 2.6 and 3.0 expose the same core workflow with different model revisions.

How to use this model

  1. 1

    Upload a clear image containing the character whose appearance should be retained.

  2. 2

    Upload a reference video in which the full action and relevant body parts remain visible.

  3. 3

    Choose whether orientation should follow the source image or the performer in the motion video.

  4. 4

    Use the prompt only to clarify the transferred action or add scene details that do not contradict the references.

  5. 5

    Choose the output mode and whether to retain the reference video's original sound, then inspect hands, feet, and occlusions closely.

2.6Available

2.6 Motion Control

Kling 2.6 Motion Control requires an image and a motion video. Character orientation can follow either source, and the original video's sound can be retained in the result.

Try now

Properties

  • Required inputs: one reference image and one reference video.
  • Configurable character orientation and original-sound retention.

How to use this model

  1. 1

    Upload the character image and the reference motion video.

  2. 2

    Choose whether orientation follows the image or video.

  3. 3

    Add only non-conflicting motion or scene guidance in the prompt.

  4. 4

    Choose output mode and whether to keep the original sound.

Examples

A reviewed video output created with 2.6 Motion Control in Omnipix.

Parameters

mode

mode
Optional

Video generation mode. 'std': Standard mode (cost-effective). 'pro': Professional mode (higher quality).

Default: std

  • std

  • pro

Image

image
Required

Reference image. The characters, backgrounds, and other elements in the generated video are based on the reference image. Supports .jpg/.jpeg/.png, max 10MB, dimensions 340px-3850px, aspect ratio 1:2.5 to 2.5:1.

Video

video
Required

Reference video. The character actions in the generated video are consistent with the reference video. Supports .mp4/.mov, max 100MB, 3-30 seconds duration depending on character_orientation.

Prompt

prompt
Optional

Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words.

Default:

Keep Original Sound

keep_original_sound
Optional

Whether to keep the original sound of the video

Default: true

Character Orientation

character_orientation
Optional

Generate the orientation of the characters in the video. 'image': same orientation as the person in the picture (max 10s video). 'video': consistent with the orientation of the characters in the video (max 30s video).

Default: image

  • image

  • video

3.0Available

3.0 motion control

The 3.0 version keeps the same image-plus-video workflow as 2.6. Use it when appearance should come from the still image and action should come from the reference clip, with optional prompt guidance and source-audio retention.

Try now

Properties

  • Required inputs: character image and motion video.
  • Supports Standard and Pro output modes and optional original audio.

How to use this model

  1. 1

    Upload a clear character image and a complete motion reference.

  2. 2

    Set character orientation to match the intended composition.

  3. 3

    Use the prompt for additions that agree with both references.

  4. 4

    Review identity, limb motion, occlusions, and retained audio.

Examples

A reviewed video output created with 3.0 motion control in Omnipix.

Parameters

mode

mode
Optional

Video generation mode. 'std': Standard mode (720p, cost-effective). 'pro': Professional mode (1080p, higher quality).

Default: pro

  • pro

  • std

Image

image
Required

Reference image. The characters, backgrounds, and other elements in the generated video are based on the reference image. Supports .jpg/.jpeg/.png, max 10MB, dimensions 340px-3850px, aspect ratio 1:2.5 to 2.5:1.

Video

video
Required

Reference video. The character actions in the generated video are consistent with the reference video. Supports .mp4/.mov, max 100MB, 3-30 seconds duration depending on character_orientation.

Prompt

prompt
Optional

Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words.

Default:

Keep Original Sound

keep_original_sound
Optional

Whether to keep the original sound of the reference video

Default: true

Character Orientation

character_orientation
Optional

Orientation of the character in the generated video. 'image': same orientation as the person in the picture (max 10s video). 'video': consistent with the orientation of the characters in the video (max 30s video). When binding elements, only 'video' orientation is supported.

Default: image

  • image

  • video