Metadata-Version: 2.1
Name: comfyui-omniavatar
Version: 1.0.0
Summary: A ComfyUI custom node developed based on OmniAvatar, capable of generating video sequences with synchronized lip movements and facial expressions by inputting a portrait image, audio, and text prompt. The node parameters and invocation method are fully consistent with the official OmniAvatar inference.
Home-page: https://github.com/CallMe1101/ComfyUI_OmniAvatar
Requires-Python: >=3.10
Requires-Dist: numpy
Requires-Dist: scipy==1.14.0
Requires-Dist: librosa==0.10.2.post1
Requires-Dist: tqdm
Requires-Dist: peft==0.15.1
Requires-Dist: transformers==4.52.3
Requires-Dist: xfuser==0.4.1
Requires-Dist: ftfy
Requires-Dist: einops
Requires-Dist: omegaconf
Requires-Dist: ffmpeg-python
Requires-Dist: dlib
Requires-Dist: face_alignment
Requires-Dist: opencv-python-headless
Requires-Dist: soundfile
Requires-Dist: Pillow
Requires-Dist: # 额外建议
Requires-Dist: # faiss-cpu   # 部分依赖（如有报错可按需安装）
Requires-Dist: # 其他依赖如bitsandbytes、gradio等仅用于训练/调试可选安装
