Claude
8fe8498df2
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
76 lines
2.9 KiB
Bash
76 lines
2.9 KiB
Bash
#!/bin/bash
|
|
# =============================================================================
|
|
# AI Photo Edit - Container Startup Script
|
|
# =============================================================================
|
|
# This script runs when the container starts. It:
|
|
# 1. Initializes the database
|
|
# 2. Downloads SAM model automatically (can be disabled with AUTO_DOWNLOAD_SAM=false)
|
|
# 3. Downloads sample eye images if the catalog is empty
|
|
# 4. Starts the FastAPI server
|
|
# =============================================================================
|
|
|
|
set -e
|
|
|
|
echo "=========================================="
|
|
echo "AI Photo Edit - Starting Up"
|
|
echo "=========================================="
|
|
|
|
# Ensure data directories exist
|
|
mkdir -p /app/data/projects
|
|
mkdir -p /app/data/patches
|
|
mkdir -p /app/data/models
|
|
mkdir -p /app/data/patch_library
|
|
|
|
# Initialize database FIRST (before eye import)
|
|
echo ""
|
|
echo "Initializing database..."
|
|
echo "------------------------------------------"
|
|
cd /app && python /scripts/init_database.py || echo "Warning: Database init failed (non-fatal)"
|
|
|
|
# Check and download SAM model automatically
|
|
echo ""
|
|
echo "Checking SAM model (Smart Select)..."
|
|
echo "------------------------------------------"
|
|
if [ -f "/app/data/models/sam_model.pth" ] || \
|
|
[ -f "/app/data/models/sam_vit_b_01ec64.pth" ] || \
|
|
[ -f "/app/data/models/sam_vit_l_0b3195.pth" ] || \
|
|
[ -f "/app/data/models/sam_vit_h_4b8939.pth" ]; then
|
|
echo "✓ SAM model found - Smart Select will use local AI (free, offline)"
|
|
else
|
|
# Auto-download SAM unless explicitly disabled
|
|
AUTO_DOWNLOAD_SAM="${AUTO_DOWNLOAD_SAM:-true}"
|
|
if [ "$AUTO_DOWNLOAD_SAM" = "true" ]; then
|
|
echo "SAM model not found. Downloading automatically..."
|
|
echo "(This is a one-time ~375MB download that persists across rebuilds)"
|
|
echo ""
|
|
python /scripts/download_sam_model.py vit_b || {
|
|
echo ""
|
|
echo "⚠ SAM download failed (non-fatal)"
|
|
echo " Smart Select will fall back to Replicate API (requires REPLICATE_API_KEY)"
|
|
echo " To retry later: docker exec -it ai-photo-edit-backend python /scripts/download_sam_model.py"
|
|
}
|
|
else
|
|
echo ""
|
|
echo "⚠ SAM model not found (AUTO_DOWNLOAD_SAM=false)"
|
|
echo ""
|
|
echo " Smart Select will use Replicate API (requires REPLICATE_API_KEY)"
|
|
echo ""
|
|
echo " To enable FREE offline Smart Select, run:"
|
|
echo " docker exec -it ai-photo-edit-backend python /scripts/download_sam_model.py"
|
|
echo ""
|
|
fi
|
|
fi
|
|
|
|
echo ""
|
|
echo "Checking GPU capabilities..."
|
|
echo "------------------------------------------"
|
|
python /scripts/gpu_setup.py || echo "Warning: GPU detection failed (non-fatal)"
|
|
|
|
echo ""
|
|
echo "=========================================="
|
|
echo "Starting FastAPI server..."
|
|
echo "=========================================="
|
|
|
|
# Start the server
|
|
exec uvicorn app.main:app --host 0.0.0.0 --port 8000
|