VACE_Wan2.1 image-to-video generation, built based on the KJ workflow, is more stable compared to the non-VACE version, reduces frame drops, maintains consistent and stable facial expressions without distortion, and eliminates the need for face repair.

By default, it generates 720P at 15 frames per second. For action prompts, retain the part before the colon and simply describe the action after the colon. The workflow includes built-in prompt optimization.

It is recommended not to use too many frames; 61 or 89 frames are suggested.

Creating content is not easy. If you find this helpful, please favorite, like, execute the application or workflow online. Your support is my motivation for creation. Thank you for your support!  

If you have any questions, please leave a comment in the comment section. I will respond promptly when I see it. Feel free to communicate, learn together, and make progress together!