Skip to content
SPECIFICTION
Get listed

CodeFormer

github.com

WebWindowsmacOSAPISelf-hosted
Visit github.com
Spec score 8.0 #17 of 30 in AI Image Restoration Software

Spec sheet

Purpose
CodeFormer is a Transformer-based method for blind face restoration that predicts codes from low-quality face images.Read 11 Oct 2026 · shangchenzhou.com
Intended users
The project page presents CodeFormer as a face-restoration method and provides code and a demo for researchers and other users working with degraded face images.Read 11 Oct 2026 · shangchenzhou.com
Integrations
The project lists Stable Diffusion WebUI, ChaiNNer, and ComfyUI among integrations, and identifies Hugging Face, Replicate, and OpenXLab demos as author-maintained deployments.Read 4 Oct 2026 · github.com
Support
The repository directs questions to [email protected].Read 11 Oct 2026 · github.com
License
The project uses the NTU S-Lab License 1.0, and the repository says redistribution and use should follow that license.Read 11 Oct 2026 · github.com
Additional tools
It includes face colorization for black-and-white or faded cropped faces and face inpainting for cropped faces masked with a white brush.Read 4 Oct 2026 · github.com
API restriction
The Replicate model page says its CodeFormer API cannot be used commercially.Read 4 Oct 2026 · replicate.com
Colorization and inpainting
Separate scripts provide colorization and inpainting for cropped and aligned face images.Read 11 Oct 2026 · github.com
Image enhancement
The project supports face restoration and whole-image enhancement, with optional Real-ESRGAN upsampling for faces and backgrounds.Read 4 Oct 2026 · github.com
Known limitation
For whole-image processing, the face-background fusion step may damage hair texture at the boundary, according to the repository's comparison note.Read 11 Oct 2026 · github.com
Local requirements
The installation instructions list PyTorch 1.7.1 or later, CUDA 10.1 or later, and additional packages in requirements.txt.Read 11 Oct 2026 · github.com
Official demos
The authors identify their Hugging Face Space, Replicate, and OpenXLab demos as official deployments they maintain.Read 11 Oct 2026 · github.com
Quality and fidelity control
A scalar weight lets users trade image quality against fidelity, with smaller values tending toward higher quality and larger values toward higher fidelity.Read 11 Oct 2026 · github.com
Quality control
A controllable weight trades image quality against fidelity, with lower values tending toward higher quality and higher values toward higher fidelity.Read 4 Oct 2026 · shangchenzhou.com
Requirements
The README lists PyTorch 1.7.1 or later, CUDA 10.1 or later, Python 3.8 in its setup example, and other packages in requirements.txt.Read 4 Oct 2026 · github.com
Restoration method
It uses a learned discrete codebook and Transformer-based code prediction to restore faces from degraded inputs.Read 4 Oct 2026 · shangchenzhou.com
Security and compliance
The opened project and demo pages do not state security certifications or compliance standards.Read 4 Oct 2026 · github.com
Third-party integrations
The repository lists integrations including Stable Diffusion WebUI and chaiNNer, and warns that other listed demos and services are third-party.Read 11 Oct 2026 · github.com
Third-party services
The README identifies other listed demos, APIs, apps, websites, and integrations as third-party and unaffiliated with the authors.Read 4 Oct 2026 · github.com
Video
The inference script accepts video input, with documented support for .mp4, .mov, and .avi files.Read 11 Oct 2026 · github.com
Video enhancement
The inference script accepts video clips ending in .mp4, .mov, or .avi; the README says Windows and Mac users should install ffmpeg first.Read 4 Oct 2026 · github.com
Whole-image enhancement
The project supports enhancing whole images and can use Real-ESRGAN to upsample faces or enhance background regions.Read 11 Oct 2026 · github.com

Where Specifiction places it

Alternatives to CodeFormerAll alternatives →