CodeFormer
Robust face restoration using codebook lookup transformer.
About
CodeFormer is a face restoration model that treats restoration as a discrete code prediction problem, using a learned codebook and a transformer to recover detail even from severely degraded faces. It handles old-photo restoration, denoising, and face inpainting, and balances fidelity against quality with an adjustable weight. Developed at NTU S-Lab. Distributed with pretrained models for research and practical use.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Image/Video Editing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
AI-powered image inpainting tool for removing objects and defects from photos.
Modular Stable Diffusion web UI focused on power users and server deployment.
Face restoration model by Tencent ARC for enhancing old or low-quality face photos.
Optimized fork of AUTOMATIC1111 with better memory management and speed.
One-click Stable Diffusion app for macOS with Apple Silicon optimization.
Image restoration using Swin Transformer for super-resolution and denoising.