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
95 lines
4.0 KiB
YAML
95 lines
4.0 KiB
YAML
# =============================================================================
|
|
# EditmaskwithAI — GPU Docker Compose (NVIDIA CUDA)
|
|
#
|
|
# Quick start:
|
|
# docker compose -f docker-compose.gpu.yml up --build
|
|
#
|
|
# Then open: http://localhost:3080
|
|
#
|
|
# What this does:
|
|
# • Detects your NVIDIA GPU at startup
|
|
# • Picks the best Stable Diffusion models for your VRAM tier
|
|
# • Auto-downloads models on first use (cached in a Docker volume)
|
|
# • Exposes local GPU generation (inpaint, outpaint, txt2img, img2img, upscale)
|
|
# • Still supports InvokeAI / ComfyUI / OpenAI via env vars below
|
|
#
|
|
# AMD ROCm: swap Dockerfile.gpu base image for a ROCm PyTorch image,
|
|
# remove the 'nvidia' driver line, and set device capabilities to [gpu].
|
|
# =============================================================================
|
|
|
|
services:
|
|
app:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.gpu
|
|
container_name: editmaskwithai-gpu
|
|
ports:
|
|
- "${PORT:-3080}:8000"
|
|
volumes:
|
|
# Persistent project data
|
|
- ./data:/app/data
|
|
# HuggingFace model cache — keeps downloaded models across rebuilds (~5-20 GB)
|
|
- hf_model_cache:/root/.cache/huggingface
|
|
# Scripts (for exec access)
|
|
- ./scripts:/scripts
|
|
environment:
|
|
# ── Local GPU (default for this compose) ────────────────────────────────
|
|
- AI_PROVIDER=${AI_PROVIDER:-local_gpu}
|
|
- AUTO_DOWNLOAD_MODELS=${AUTO_DOWNLOAD_MODELS:-true}
|
|
|
|
# ── Per-operation overrides (optional) ──────────────────────────────────
|
|
# Leave blank to use AI_PROVIDER for all operations.
|
|
# Example: use InvokeAI for inpaint, local GPU for everything else:
|
|
# AI_PROVIDER_INPAINT=invokeai
|
|
- AI_PROVIDER_INPAINT=${AI_PROVIDER_INPAINT:-}
|
|
- AI_PROVIDER_TXT2IMG=${AI_PROVIDER_TXT2IMG:-}
|
|
- AI_PROVIDER_IMG2IMG=${AI_PROVIDER_IMG2IMG:-}
|
|
- AI_PROVIDER_OUTPAINT=${AI_PROVIDER_OUTPAINT:-}
|
|
|
|
# ── Remote/cloud providers (all optional) ────────────────────────────────
|
|
- OPENAI_API_KEY=${OPENAI_API_KEY:-}
|
|
- OPENAI_MODEL=${OPENAI_MODEL:-dall-e-3}
|
|
- REPLICATE_API_KEY=${REPLICATE_API_KEY:-}
|
|
- STABILITY_API_KEY=${STABILITY_API_KEY:-}
|
|
|
|
# ── InvokeAI / ComfyUI (running on another machine or container) ────────
|
|
- INVOKEAI_URL=${INVOKEAI_URL:-}
|
|
- INVOKEAI_DEFAULT_MODEL=${INVOKEAI_DEFAULT_MODEL:-flux-dev}
|
|
- COMFYUI_URL=${COMFYUI_URL:-}
|
|
- COMFYUI_DEFAULT_MODEL=${COMFYUI_DEFAULT_MODEL:-v1-5-pruned-emaonly.ckpt}
|
|
|
|
# ── HuggingFace model overrides (optional) ───────────────────────────────
|
|
# Override the auto-selected model for any operation:
|
|
# HF_MODEL_INPAINT=your-org/your-model
|
|
- HF_MODEL_INPAINT=${HF_MODEL_INPAINT:-}
|
|
- HF_MODEL_TXT2IMG=${HF_MODEL_TXT2IMG:-}
|
|
- HF_MODEL_IMG2IMG=${HF_MODEL_IMG2IMG:-}
|
|
- HF_TOKEN=${HF_TOKEN:-}
|
|
|
|
# ── App settings ─────────────────────────────────────────────────────────
|
|
- DATABASE_URL=sqlite:///./data/ai_photo_edit.db
|
|
- SECRET_KEY=${SECRET_KEY:-change-this-secret-key-in-production}
|
|
- CORS_ORIGINS=*
|
|
- AUTO_DOWNLOAD_SAM=${AUTO_DOWNLOAD_SAM:-true}
|
|
|
|
# NVIDIA GPU passthrough — requires nvidia-container-toolkit on the host.
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
|
|
# Reliable DNS for HuggingFace Hub downloads and external API calls
|
|
dns:
|
|
- 8.8.8.8
|
|
- 8.8.4.4
|
|
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
hf_model_cache:
|
|
# Survives docker compose down; delete manually to free disk space:
|
|
# docker volume rm editmaskwithai_hf_model_cache
|