This is the workflow for redrawing mouth movements based on audio!
Usage
1. Upload the video
2. Fill in the long side dimensions
3、Upload audio
4. Fill in the start and end times of the audio
5. Fill in the prompt words
Video long side 832, generating a 5-second video takes 3 minutes, long side 1024, 10-second video takes 5 minutes, long side 1280, 10-second video takes 7 minutes
You can click on 【Test Effect】, and if you're satisfied with the result, you can download the workflow to deploy locally!