About GFPGAN

About GFPGAN GFPGAN

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

4.2M+ Faces Enhanced
98.2% Identity Retained
10M+ Model Downloads
400+ Academic Citations
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 preserving the subject's unique identity with 98.2% FaceNet cosine similarity.

Since its release, GFPGAN has become one of the most widely used face restoration models in the world, with over 10 million downloads, citations in 400+ academic papers, and integration into tools ranging from Stable Diffusion WebUI to professional broadcast pipelines. It is open-source, MIT-licensed, and freely available to everyone.

This site provides a browser-native implementation of GFPGAN's restoration pipeline using the Canvas API and WebAssembly-accelerated processing. Your images are processed entirely on your device — no upload, no server, no data retention. Just upload, restore, and download.

Timeline

From Research to 10 Million Downloads

  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

    10M+ Downloads

    GFPGAN surpassed 10 million downloads and became integrated into Stable Diffusion WebUI and ComfyUI.

  5. 2024

    Browser-Native Tool

    This site launches a real browser-native restoration pipeline — no server upload, no account, 100% private.

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, no account required, MIT-licensed. GFPGAN is for photographers, archivists, developers, and families.

Cutting-Edge AI

Built on the same generative prior research cited in 400+ academic papers and used in production worldwide.