kwaivgi/kling-v3-motion-control
Kling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image * | string (uri) | 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 * | string (uri) | 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. | — | — |
character_orientation | string | 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. | "image" | image video |
keep_original_sound | boolean | Whether to keep the original sound of the reference video | true | — |
mode | string | Video generation mode. 'std': Standard mode (720p, cost-effective). 'pro': Professional mode (1080p, higher quality). | "pro" | std pro |
prompt | string | Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words. | "" | — |
image required string 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 required string 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.
character_orientation string 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.
"image" keep_original_sound boolean Whether to keep the original sound of the reference video
true mode string Video generation mode. 'std': Standard mode (720p, cost-effective). 'pro': Professional mode (1080p, higher quality).
"pro" prompt string Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words.
"" 15430b300f8c Updated: 6/26/2026 309.9K runs
cinemasetfree.com