⚛️ GAN-MASTER

An optimized AI tool support image restoration, image denoise, upscale, ... using GFP-GAN, GPEN, ...

⚠️ Important Note
🌵 I only have RTX 30 series (SM86). So newer series untested.
🌵 If you facing any issue, please send the error log to:
     💮 LinkedIn
     💮 Facebook
     💮 Whatsapp

🌵 Compatible GPU
✅ SM86Newer	RTXRunnable, 40but Series.slower.
✅ SM86	RTX 30 Series.
⛔ Unsupported	RTX 20 Series and older, AMD or Intel GPU.

🌸 Quick Start (Docker Compose)

Install Docker, Newest Nvidia Driver & CUDA toolkit
Next, copy docker-compose.yml content below and put to empty folder.
Then, open Terminal/CMD/Windows PowerShell and navigate to directory contain docker-compose.yml file.
Finally, run this command docker compose up -d to start the container. Go to http://localhost:7860 and enjoy.

Requirements

⬇️ Docker
⬇️ nvidia-driver
⬇️ cuda-toolkit

Models (download then copy into models folder

⬇️ RetinaFace-R50
⬇️ ParseNet-latest
⬇️ realesrnet_x4
⬇️ GPEN-BFR-512
⬇️ Colorization
⬇️ RealESRGAN_x2plus
⬇️ GFPGANv1.4

docker-compose.yml

services:
  gan-master:
    image: sandichhuu/gan-master:sm86cu130
    container_name: gan-master
    ipc: host
    port:
      - 7860:7860
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    volumes:
      - ./models:/workspace/app/models
      - ./outputs:/workspace/app/outputs

🌸 Setup Structure

comfyuv/
├── docker-compose.yml
├── models/
└── output/