No. 16 of 29 ·AI Image Restoration Software

CodeFormer

Web · Self-hosted · API

Visit site Alternatives

Freedom report

One barScore 5.3

Free tierNo free tier on record
Open codeNo open-source code on record
Runs widely1 of 6 device platforms
DocumentedPlans, terms and facts published

CodeFormer is ranked #16 of 29 in AI image restoration software on Freedom251. It runs on API, Self-hosted, Web.

Compared on AI image restoration software

Fading repair: Yes
Face restoration: Yes

Best CodeFormer alternatives

See all 20

Two bars Cutout.Pro Free tier No. 1$4.99/mo6.8 Two bars ImageColorizer Free tier No. 2$6.90/mo6.6 Two bars PicWish Old Photo Restoration Free tier No. 3Free6.6 Two bars insMind AI Photo Restoration Free tier No. 4Free6.5 Two bars Pixelcut Free tier No. 5Free6.5 One bar LetsEnhance Free tier No. 6$9/mo6.3

The record

Purpose: CodeFormer is a robust blind face restoration method designed to restore faces in old photos and AI-generated images.
Restoration method: It uses a learned discrete codebook and Transformer-based code prediction to restore faces from degraded inputs.
Quality control: A controllable weight trades image quality against fidelity, with lower values tending toward higher quality and higher values toward higher fidelity.
Image enhancement: The project supports face restoration and whole-image enhancement, with optional Real-ESRGAN upsampling for faces and backgrounds.
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.
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.
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.
Integrations: The project lists Stable Diffusion WebUI, ChaiNNer, and ComfyUI among integrations, and identifies Hugging Face, Replicate, and OpenXLab demos as author-maintained deployments.
Third-party services: The README identifies other listed demos, APIs, apps, websites, and integrations as third-party and unaffiliated with the authors.
License: The project uses the NTU S-Lab License 1.0, and the Replicate model page says redistribution and use for non-commercial purposes should follow that license.
API restriction: The Replicate model page says its CodeFormer API cannot be used commercially.
Security and compliance: The opened project and demo pages do not state security certifications or compliance standards.
Support: The project README provides [email protected] for questions.
Intended users: The project page presents CodeFormer as a research method and asks users who use its dataset or paper to cite the work.

Where it ranks on Freedom251

Best AI Image Restoration Software in 2026#16 of 29

Is CodeFormer yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote CodeFormer

Sources

github.com/sczhou/CodeFormer· checked 4 Oct 2026
shangchenzhou.com/projects/CodeFormer/· checked 4 Oct 2026
replicate.com/sczhou/codeformer· checked 4 Oct 2026