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 image generation app for Apple devices with on-device processing.
Optimized fork of AUTOMATIC1111 with better memory management and speed.
Face restoration model by Tencent ARC for enhancing old or low-quality face photos.
AI-powered image inpainting tool for removing objects and defects from photos.
Image restoration using Swin Transformer for super-resolution and denoising.
Feature-rich web UI for Stable Diffusion with extensive extension ecosystem.