Claude
43c66ea860
dall-e-2/dall-e-3 retired May 12 2026 and gpt-image-1 deprecates Oct 23 2026, so move every OpenAI default (config.py, both provider classes, both compose files, .env.example, the in-app provider-settings dropdown, README) to gpt-image-2 for both generation and edits. Also fix response parsing in ai_provider.py's OpenAIProvider, which never sent a model param and assumed a url response — gpt-image-1/2 only return b64_json. Separately, .env.example shipped AI_PROVIDER=replicate by default, but replicate has no driver in remote_provider.py, so following the documented "cp .env.example .env" setup silently broke every AI call and defeated the GPU quick-start (an explicit non-empty .env value overrides docker-compose.gpu.yml's own local_gpu fallback). Default to local_gpu instead, mark replicate/stability as not-yet-implemented, and recommend Lykon/dreamshaper-8-inpainting as a hands/face-tuned HF_MODEL_INPAINT override for 4-6GB cards (Quadro P2200, GTX 1060/1660). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Nb2vJ8W7bHKx1JXVvpCraH
150 lines
7.3 KiB
YAML
150 lines
7.3 KiB
YAML
# =============================================================================
|
||
# EditmaskwithAI — GPU Docker Compose (NVIDIA CUDA)
|
||
#
|
||
# ── PREREQUISITES ─────────────────────────────────────────────────────────────
|
||
#
|
||
# 1. NVIDIA driver ≥ 525 installed on the host
|
||
# Check: nvidia-smi
|
||
#
|
||
# 2. nvidia-container-toolkit installed and configured:
|
||
# (Ubuntu/Debian)
|
||
# curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
|
||
# | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-ctk.gpg
|
||
# curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
|
||
# | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-ctk.gpg] https://#g' \
|
||
# | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
|
||
# sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
|
||
# sudo nvidia-ctk runtime configure --runtime=docker
|
||
# sudo systemctl restart docker
|
||
#
|
||
# (RHEL/Fedora/Rocky)
|
||
# sudo dnf install -y nvidia-container-toolkit
|
||
# sudo nvidia-ctk runtime configure --runtime=docker
|
||
# sudo systemctl restart docker
|
||
#
|
||
# 3. Verify GPU access in Docker:
|
||
# docker run --rm --gpus all nvidia/cuda:12.1.0-base-ubuntu22.04 nvidia-smi
|
||
#
|
||
# ── QUICK START ───────────────────────────────────────────────────────────────
|
||
#
|
||
# docker compose -f docker-compose.gpu.yml up --build
|
||
# Then open: http://localhost:3080
|
||
#
|
||
# ── OLDER DOCKER SETUPS (docker-compose v1 / nvidia-docker2) ─────────────────
|
||
#
|
||
# If you installed nvidia-docker2 (older approach) instead of nvidia-container-toolkit,
|
||
# replace the 'deploy:' block below with:
|
||
#
|
||
# runtime: nvidia
|
||
# environment:
|
||
# - NVIDIA_VISIBLE_DEVICES=all
|
||
# - NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
||
#
|
||
# ── GPU TIER AUTO-SELECTION ───────────────────────────────────────────────────
|
||
#
|
||
# ≥16 GB VRAM → SDXL (best quality)
|
||
# 8–16 GB → SDXL
|
||
# 4–8 GB → Stable Diffusion 2.x
|
||
# 2–4 GB → Stable Diffusion 1.5 (older GPUs: GTX 970/1060/RX 580)
|
||
# <2 GB → SD 1.5 + CPU offload (very slow — consider a remote provider)
|
||
#
|
||
# ── AMD ROCm ──────────────────────────────────────────────────────────────────
|
||
#
|
||
# Swap the base image in Dockerfile.gpu:
|
||
# FROM pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime
|
||
# → FROM rocm/pytorch:rocm6.0_ubuntu22.04_py3.9_pytorch_2.1.0
|
||
# Remove the 'driver: nvidia' line and add: device_ids: ['0']
|
||
#
|
||
# =============================================================================
|
||
|
||
services:
|
||
app:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile.gpu
|
||
args:
|
||
# Increment BUILDID to force pip layers to re-run without full --no-cache:
|
||
# BUILDID=$(date +%s) docker compose -f docker-compose.gpu.yml up --build
|
||
BUILDID: ${BUILDID:-1}
|
||
container_name: paintplus
|
||
ports:
|
||
- "${PORT:-3080}:8000"
|
||
volumes:
|
||
# Persistent project data
|
||
- ./data:/app/data
|
||
# HuggingFace model cache — bind mount so models can be pre-downloaded on the host.
|
||
# If container DNS is blocked, run ./prefetch-models.sh on the host first —
|
||
# it downloads BEN2/BiRefNet-HR (and optionally SDXL with --sdxl) straight
|
||
# into this directory, and the container picks them up on next start.
|
||
# To free disk space: rm -rf ./data/hf_cache
|
||
- ./data/hf_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:-gpt-image-2}
|
||
- OPENAI_EDIT_MODEL=${OPENAI_EDIT_MODEL:-gpt-image-2}
|
||
- REPLICATE_API_KEY=${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=${AUTO_DOWNLOAD_SAM:-true}
|
||
- AUTO_DOWNLOAD_U2NET=${AUTO_DOWNLOAD_U2NET:-true}
|
||
- BG_REMOVAL_MODEL=${BG_REMOVAL_MODEL:-ben2}
|
||
|
||
# ── NVIDIA GPU passthrough ────────────────────────────────────────────────
|
||
# Requires nvidia-container-toolkit; see prerequisites at top of this file.
|
||
# For older nvidia-docker2 setups, replace this block with:
|
||
# runtime: nvidia
|
||
# environment:
|
||
# - NVIDIA_VISIBLE_DEVICES=all
|
||
deploy:
|
||
resources:
|
||
reservations:
|
||
devices:
|
||
- driver: nvidia
|
||
count: 1
|
||
capabilities: [gpu]
|
||
|
||
# DNS: try host resolver first (works on most networks including corporate/VPN),
|
||
# fall back to Cloudflare then Google public resolvers.
|
||
# If all three fail (Errno -3), your firewall is blocking port 53 UDP from Docker.
|
||
# Fix on the host: sudo iptables -I DOCKER-USER -p udp --dport 53 -j ACCEPT
|
||
dns:
|
||
- 1.1.1.1
|
||
- 8.8.8.8
|
||
- 8.8.4.4
|
||
|
||
restart: unless-stopped
|