Add local GPU inference: auto-detect GPU, auto-download best diffusion models

Adds AI_PROVIDER=local_gpu — a fully self-contained GPU inference engine
using HuggingFace Diffusers that requires zero InvokeAI/ComfyUI setup.
All existing providers (InvokeAI, ComfyUI, OpenAI, Replicate) remain intact
and can be mixed with local GPU via per-operation overrides.

New features:
- GPU auto-detection (CUDA/NVIDIA, MPS/Apple Silicon, CPU fallback)
- VRAM-tiered model selection:
    ultra ≥16 GB → SDXL inpaint + SDXL base
    high  8-16 GB → SDXL inpaint + SDXL base
    medium 4-8 GB → SD 2.x inpaint + SD 2.1
    low  <4 GB   → SD 2.x (small)
- Auto-download model weights to HuggingFace disk cache at startup
  (background task; first request loads from local disk, not internet)
- LRU pipeline cache evicts oldest GPU pipeline when VRAM limit reached
- Per-operation model overrides via HF_MODEL_INPAINT / HF_MODEL_TXT2IMG etc.
- Optional HF_TOKEN for gated/private HuggingFace models

New files:
- backend/app/services/gpu_detect.py   — GPU detection + tier/model mapping
- backend/app/services/local_diffusion.py — Diffusers provider + LRU cache
- backend/app/routers/gpu_status.py    — GET /api/gpu/status, POST /api/gpu/prefetch
- backend/requirements.gpu.txt         — Diffusers ecosystem deps (GPU only)
- docker-compose.gpu.yml               — NVIDIA GPU compose (one-command startup)
- Dockerfile.gpu                       — pytorch/pytorch:2.1.0-cuda12.1 base image
- scripts/gpu_setup.py                 — Startup GPU info logger

Modified:
- backend/app/config.py                — local_gpu settings added
- backend/app/services/remote_provider.py — local_gpu registered as provider
- backend/app/routers/ai_tools.py      — /api/config exposes GPU tier + caps
- backend/app/main.py                  — GPU router + background prefetch task
- backend/entrypoint.sh                — runs gpu_setup.py at container start
- .env.example                         — local_gpu documented as first option

Quick start with GPU:
  docker compose -f docker-compose.gpu.yml up --build

https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM

Dockerfile.gpu

@@ -0,0 +1,75 @@
+# =============================================================================
+# 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
+COPY backend/requirements.txt .
+COPY backend/requirements.gpu.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+RUN 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"]