Wan2.2-S2V in ComfyUI: Audio-Driven Video
ComfyUI's native workflow for Wan2.2-S2V, which turns a still image plus audio into a talking or singing video. It supports full-body and half-body characters and long-form output.
Key points
- Image + audio in, synchronized video out
- Dialogue, singing and performance
- Minute-level generation
- Text instructions control actions and scene