kwaivgi/kling-v2.6-motion-control ❓🖼️📝✓ → 🖼️
About
Enables precise control of character actions and expressions from a reference image.
Example Output
Output
Performance Metrics
390.39s
Prediction Time
390.44s
Total Time
All Input Parameters
{
"mode": "pro",
"image": "https://replicate.delivery/pbxt/OHMFuZ6vHcDd3sXoOnn5oGLBvZIq43HuAige2XeWLdBigLUs/santa.png",
"video": "https://replicate.delivery/pbxt/OHMFv2w6blsLcBTvRSEujuJnNvRNXXEmyLlXIvpMSVzG8mhN/taichi.mp4",
"prompt": "",
"keep_original_sound": true,
"character_orientation": "image"
}
Input Parameters
- mode
- Video generation mode. 'std': Standard mode (cost-effective). 'pro': Professional mode (higher quality).
- 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 (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
- Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words.
- keep_original_sound
- Whether to keep the original sound of the video
- character_orientation
- 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).
Output Schema
Output
Example Execution Logs
Uploading image and video to GCP... Using model: kling-v2-6-motion-control in pro mode Generating motion control video... Generated video in 379.1sec Generated video ID: 832113290510729296 Downloading 17667428 bytes Downloaded 16.85MB in 9.58sec
Version Details
- Version ID
0b9053d30c02c3b6574ddf14f33499f7b69302c81954ad86239fa67bc5e52896- Version Created
- December 22, 2025