This project combines audio-driven lip-syncing with beat-synchronized animations into a single cohesive node for ComfyUI.
- Lip-Sync Animations: Uses Echo Mimic for phoneme-to-viseme mapping and animation.
- Beat-Synchronized Gestures: Generates body and hand movements aligned with music beats.
- Outputs Frames: Produces individual animation frames for combination into a video.
-
Clone this repository.
-
Install the required dependencies:
pip install -r requirements.txt
-
Place your input files in the
inputs/
folder:- An image (e.g.,
image.jpg
). - An audio file (e.g.,
audio.mp3
).
- An image (e.g.,
-
Run the script:
python src/main.py
Animation frames are saved in the outputs/
directory.
MIT License