# TencentARC/GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Repository: https://github.com/TencentARC/GFPGAN
Canonical: https://ross.abutalabs.com/products/gfpgan
Language: Python
License: NOASSERTION
License Family: other
Topics: pytorch, gan, deep-learning, super-resolution, face-restoration, image-restoration, gfpgan
Last push: 2024-07-26T18:44:02+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1993, "days_push": 768, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 37657, forks 6292 (observed 2026-08-28T04:12:01.516387+00:00)

## What it is
GFPGAN is a Python library built on PyTorch that restores and enhances real-world degraded face photos using GAN-based priors. It provides pretrained models and a CLI/inference API for blind face restoration and super-resolution.

## Use cases
- restore old blurry face photos
- enhance low-quality portrait images
- upscale faces in photos with super-resolution
- fix faces in AI-generated images
- batch enhance family photo archives
- integrate face restoration into an image pipeline

## When to choose
- you need practical, pretrained blind face restoration without training your own model
- you want a pip-installable PyTorch library with CPU and GPU support
- you need to enhance faces in real-world degraded photos

## When to avoid
- you need general image restoration beyond faces
- you require a permissively licensed dependency (license is non-standard despite Apache badge)
- you need actively developed cutting-edge models, as development has slowed

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: face-restoration, super-resolution, gan, pytorch, image-enhancement

## Member repositories
- TencentARC/GFPGAN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.516387+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:25:22.593103+00:00, confidence not recorded.
  - readme: https://github.com/TencentARC/GFPGAN (fetched 2026-08-28T04:12:01.516387+00:00, sha f44a3b43dd52)
  - registry_pypi: https://pypi.org/pypi/gfpgan/json (fetched 2026-08-29T07:47:08.145481+00:00, sha 56d145b2446a)
- Data as of 2026-08-30T08:39:29.467469+00:00.