Dockerfile

FROM anchorxia/musev:latest

LABEL MAINTAINER="zkangchen"
LABEL Description="musev gradio image, from docker pull anchorxia/musev:latest"

SHELL ["/bin/bash", "--login", "-c"]

RUN useradd -m -u 1000 user
USER user

ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH

WORKDIR $HOME/app

RUN echo "docker start" \
  && whoami \
  && which python \
  && pwd

RUN git clone -b main --recursive https://github.com/TMElyralab/MuseTalk.git
RUN chmod -R 777 /home/user/app/MuseTalk

RUN . /opt/conda/etc/profile.d/conda.sh \
    && echo "source activate musev" >> ~/.bashrc \
    && conda activate musev \
    && conda env list

RUN ffmpeg -codecs

WORKDIR /home/user/app/MuseTalk/

RUN pip install -r requirements.txt \
    && pip install --no-cache-dir -U openmim \
    && mim install mmengine \
    && mim install "mmcv>=2.0.1" \
    && mim install "mmdet>=3.1.0" \
    && mim install "mmpose>=1.1.0"

RUN pip install -q -U "huggingface_hub<1.0"

# Download models at build time (cached in Docker layer)
RUN . /opt/conda/etc/profile.d/conda.sh && conda activate musev && \
    mkdir -p models/musetalk models/musetalkV15 models/syncnet \
      models/dwpose models/face-parse-bisent models/sd-vae models/whisper && \
    huggingface-cli download TMElyralab/MuseTalk \
      --local-dir models \
      --include "musetalkV15/musetalk.json" "musetalkV15/unet.pth" && \
    huggingface-cli download stabilityai/sd-vae-ft-mse \
      --local-dir models/sd-vae \
      --include "config.json" "diffusion_pytorch_model.bin" "diffusion_pytorch_model.safetensors" && \
    huggingface-cli download openai/whisper-tiny \
      --local-dir models/whisper \
      --include "config.json" "pytorch_model.bin" "preprocessor_config.json" && \
    huggingface-cli download yzd-v/DWPose \
      --local-dir models/dwpose \
      --include "dw-ll_ucoco_384.pth" && \
    huggingface-cli download ByteDance/LatentSync \
      --local-dir models/syncnet \
      --include "latentsync_syncnet.pt" && \
    curl -sL https://download.pytorch.org/models/resnet18-5c106cde.pth \
      -o models/face-parse-bisent/resnet18-5c106cde.pth && \
    python -c "import gdown; gdown.download(id='154JgKpzCPW82qINcVieuPH3fZ2e0P812', output='models/face-parse-bisent/79999_iter.pth', quiet=False)" && \
    echo "All models downloaded"

COPY --chown=user:user app.py /home/user/app/MuseTalk/app.py
COPY --chown=user:user entrypoint.sh /home/user/app/MuseTalk/entrypoint.sh
RUN chmod +x /home/user/app/MuseTalk/entrypoint.sh

EXPOSE 7860

CMD ["./entrypoint.sh"]