About

About GFPGAN — AI Face Restoration Research & Technology

The AI technology, the research team, and the mission behind the world's leading open-source face restoration model.

CVPR 2021 Published Research
Tencent ARC Model Developer
v1.2-v1.4 Released Weights
Open Source & Weights
The Story

What is GFPGAN?

GFPGAN (Generative Facial Prior GAN) is a landmark AI face restoration model created by Xintao Wang, Yu Li, Honglun Zhang, and Ying Shan at Tencent Research (ARC Lab) and first presented at CVPR 2021.

The model solves a fundamental challenge in face restoration: how do you recover realistic, high-fidelity detail from a photo where that detail no longer exists? GFPGAN's answer is the Generative Facial Prior — a rich facial knowledge base extracted from a pre-trained StyleGAN2 that contains the natural statistics of real faces. By incorporating this prior into the restoration pipeline, GFPGAN can reconstruct eyes, skin texture, hair, and expression with extraordinary realism.

Unlike simple sharpening or upscaling tools, GFPGAN understands what faces should look like. It detects and aligns facial landmarks, encodes the specific degradation pattern of the input, applies the generative prior to fill in missing or corrupted detail, and seamlessly composites the result back onto the original image — all while working to preserve the subject's unique identity rather than inventing a plausible new face.

Since its release, GFPGAN has become one of the most widely used face restoration models in the world, cited throughout the blind-face-restoration literature and integrated into tools ranging from Stable Diffusion WebUI to ComfyUI. The weights and code are published openly by Tencent ARC on GitHub, where the current licence terms are stated.

This site is independent documentation for GFPGAN, plus a free browser-based photo enhancer. The enhancer is a classical Canvas-API filter — tone mapping, artifact smoothing and unsharp masking — that runs entirely on your device with no upload, no server and no data retention. It is not the GFPGAN neural network; our guides explain how to run the real model locally or on a hosted GPU.

Timeline

From CVPR Paper to Everyday Tool

  1. 2021

    CVPR Paper

    GFPGAN research published at CVPR 2021 by Tencent ARC Lab, introducing the Generative Facial Prior concept.

  2. 2021

    Open-Source Release

    Model weights and full training code released on GitHub under the TencentARC organisation.

  3. 2022

    v1.3 & v1.4

    Improved model variants released with higher resolution output (1024px) and better identity fidelity.

  4. 2023

    Mainstream Adoption

    GFPGAN became a built-in face-restoration option in Stable Diffusion WebUI and a widely used ComfyUI extension.

  5. 2024

    This Site Launches

    We began publishing independent, tested documentation for GFPGAN, alongside a free browser-based photo enhancer that runs locally with no upload.

Our Principles

What We Stand For

Privacy First

Every image processed on this site stays on your device. Zero upload. Zero storage. Zero compromise.

Scientific Accuracy

Results are benchmarked with FaceNet cosine similarity — not just visual impressions. Numbers matter.

Open for Everyone

Free to read, no account required. GFPGAN itself is open-source — for photographers, archivists, developers, and families.

Cutting-Edge AI

Built on the Generative Facial Prior research published at CVPR 2021 and used in production pipelines worldwide.