Claude
11772e620c
Build / pip layer fixes:
- Add BUILDID ARG to Dockerfile.gpu; pass from docker-compose.gpu.yml build args
so pip layers can be force-busted without --no-cache:
BUILDID=$(date +%s) docker compose -f docker-compose.gpu.yml up --build
Model download (DNS-blocked environments):
- Change HF model cache from named volume to ./data/hf_cache bind mount
so models can be pre-downloaded on the host (no rebuild needed)
- Remove now-unused hf_model_cache named volume
- README: add iptables fix + huggingface-cli offline download instructions
Error handling improvements:
- ai_edit_region: catch ConnectError/Errno-3 → return 503 with exact fix commands
- _require_remote: give actionable message when local_gpu provider fails to load
- _build_provider: catch AttributeError (torch.xpu from wrong diffusers) not just ImportError
- local_diffusion.py: fix docstring to reflect <0.29.0 pin
https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM
79 lines
2.8 KiB
Docker
79 lines
2.8 KiB
Docker
# =============================================================================
|
|
# EditmaskwithAI — GPU Container (NVIDIA CUDA)
|
|
#
|
|
# Usage:
|
|
# docker compose -f docker-compose.gpu.yml up --build
|
|
#
|
|
# Requirements on host:
|
|
# - NVIDIA driver ≥ 525 (for CUDA 12.x)
|
|
# - nvidia-container-toolkit installed and configured
|
|
# - docker compose v2 (or docker-compose with GPU device support)
|
|
#
|
|
# AMD ROCm users: replace the pytorch base image with a ROCm variant, e.g.
|
|
# rocm/pytorch:latest (and remove the nvidia-smi check below)
|
|
# =============================================================================
|
|
|
|
# ── Stage 1: Build miniPaint frontend ────────────────────────────────────────
|
|
FROM node:20-alpine AS frontend-build
|
|
|
|
WORKDIR /frontend
|
|
COPY frontend/package.json frontend/package-lock.json* ./
|
|
RUN npm install
|
|
COPY frontend/ ./
|
|
RUN npm run build
|
|
|
|
# ── Stage 2: PyTorch CUDA runtime ────────────────────────────────────────────
|
|
# pytorch/pytorch already includes torch + torchvision built for CUDA 12.1.
|
|
# Using the runtime (not devel) image keeps the layer lean.
|
|
FROM pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime
|
|
|
|
WORKDIR /app
|
|
|
|
# System dependencies
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
libgl1 \
|
|
libglib2.0-0 \
|
|
libsm6 \
|
|
libxext6 \
|
|
libxrender-dev \
|
|
libgomp1 \
|
|
wget \
|
|
git \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install Python dependencies — base + GPU extras
|
|
# BUILDID forces pip layers to re-run when you need fresh packages without a full --no-cache:
|
|
# BUILDID=$(date +%s) docker compose -f docker-compose.gpu.yml up --build
|
|
ARG BUILDID=1
|
|
COPY backend/requirements.txt .
|
|
COPY backend/requirements.gpu.txt .
|
|
RUN echo "BUILDID=$BUILDID" && pip install --no-cache-dir -r requirements.txt
|
|
RUN echo "BUILDID=$BUILDID" && pip install --no-cache-dir -r requirements.gpu.txt
|
|
|
|
# Smoke-test rembg (model downloads on first use)
|
|
RUN python -c "from rembg import remove; print('rembg OK')" \
|
|
|| echo "WARNING: rembg unavailable — Remove Background disabled"
|
|
|
|
# Copy backend application
|
|
COPY backend/ .
|
|
|
|
# Entrypoint
|
|
COPY backend/entrypoint.sh /entrypoint.sh
|
|
RUN chmod +x /entrypoint.sh
|
|
|
|
# Scripts (SAM download, DB init, GPU setup, etc.)
|
|
COPY scripts/ /scripts/
|
|
RUN chmod +x /scripts/*.py 2>/dev/null || true
|
|
|
|
# Copy built frontend from Stage 1
|
|
COPY --from=frontend-build /frontend/index.html /app/static/
|
|
COPY --from=frontend-build /frontend/dist /app/static/dist
|
|
COPY --from=frontend-build /frontend/images /app/static/images
|
|
COPY --from=frontend-build /frontend/src/css /app/static/src/css
|
|
|
|
# Persistent data directories
|
|
RUN mkdir -p /app/data/projects /app/data/patches /app/data/models
|
|
|
|
EXPOSE 8000
|
|
ENTRYPOINT ["/entrypoint.sh"]
|