ComfyUI-Hallo

ComfyUI-Hallo
★ 309

ComfyUI集成hallo集成媒体处理需FFmpeg
ComfyUI 的自定义节点，将 hallo 项目的能力接入 ComfyUI，使在节点流程中便捷生成与处理媒体，需 FFmpeg 支持。
💡 在 ComfyUI 中直接使用 hallo 生成或处理媒体文件。
🍴 14 Forks💻 Python🔄 2024-06-24
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/b6135d9bd930
📦 requirements.txt
diffusers
omegaconf
librosa
audio-separator
onnxruntime-gpu
opencv-python
onnx2torch
onnx
moviepy
accelerate
av
bitsandbytes
decord
einops
insightface
mediapipe[vision]==0.10.14
mlflow
tqdm
isort
pylint
pre-commit
📄 README

ComfyUI-Hallo

a comfyui custom node for hallo

How to use

make sure ffmpeg is worked in your commandline

for Linux

apt update
apt install ffmpeg

for Windows,you can install ffmpeg by WingetUI automatically

then!

## insatll xformers match your torch,for torch==2.1.0+cu121
pip install xformers==0.0.22.post7
pip install accelerate 
# in ComfyUI/custom_nodes
git clone https://github.com/AIFSH/ComfyUI-Hallo.git
cd ComfyUI-Hallo
pip install -r requirements.txt

weights will be downloaded from huggingface,or can mamually download from fudan-generative-ai/hallo,and put them all in ComfyUI-Hallo/pretrained_models

Tutorial

  • Demo

    • WeChat Group

    Thanks

    hallo