Ubuntu下制作ComfyUI的镜像文件

1、创建名为comfyui-docker的文件夹，并创建Dockerfile文件，文件中的内容如下：

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive

ENV PYTHONUNBUFFERED=1

RUN apt-get update && apt-get install -y \

    git \

    curl \

    wget \

    ffmpeg \

    libsm6 \

    libxext6 \

    libgl1 \

    python3 \

    python3-pip \

    python3-venv \

    && rm -rf /var/lib/apt/lists/*

WORKDIR /workspace

RUN git clone https://githubfast.com/comfyanonymous/ComfyUI.git .

RUN pip3 install --timeout 300 -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

EXPOSE 8188

CMD ["python3", "main.py","--listen","0.0.0.0","--port","8188"]

2、构建镜像：

docker build -t comfyui-cuda .

3、创建并启动容器：

docker run -it --rm -p 8188:8188 --gpus all --name comfyui comfyui-cuda