whosouravsharma's picture
Add inference backend: Gradio /generate endpoint over SD 1.5 + LoRA
4ff39a4 verified
Raw History Blame Contribute Delete
976 Bytes
# Only needed if you run this outside a Gradio Space (locally, or as an
# sdk: docker Space). A plain `sdk: gradio` Space builds its own container
# from requirements.txt and does not use this file.
FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive \
PYTHONUNBUFFERED=1 \
PIP_NO_CACHE_DIR=1
RUN apt-get update && apt-get install -y --no-install-recommends \
python3.10 python3-pip git && \
rm -rf /var/lib/apt/lists/*
# Spaces run as uid 1000 and only $HOME is writable; the model cache must
# live somewhere this user can actually write or startup fails.
RUN useradd -m -u 1000 app
USER app
ENV HOME=/home/app \
HF_HOME=/home/app/.cache/huggingface \
PATH=/home/app/.local/bin:$PATH
WORKDIR /home/app
COPY --chown=app requirements.txt .
RUN pip3 install --user --no-cache-dir -r requirements.txt
COPY --chown=app app.py ./
COPY --chown=app src/ ./src/
EXPOSE 7860
ENV PORT=7860
CMD ["python3", "app.py"]