Generate video based on specified actions for images

The resolution of the images should match the resolution of the reference video. Generating low-resolution or long videos may cause facial distortion. It is recommended to use my quick face-swapping workflow for facial repair.

The default number of generated frames and skipped reference video frames is 0.

Creating is not easy. If this has helped you, please save more, execute applications or workflows online more. Everyone's support is my motivation for creation. Thank you for your support!

If you have any questions, please leave a comment, and I will reply promptly when I see it. Welcome to exchange, learn together, and make progress together!