LibreAI / Imagem / GFPGAN
// image · TencentARC/GFPGAN

GFPGAN

GFPGAN é um projeto de imagem de código aberto de TencentARC (TencentARC/GFPGAN no GitHub). Tem 37.703 estrelas no GitHub e 6.279 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 26 de julho de 2024.

Tencent ARC face restoration — revives old, blurry and low-quality faces with a StyleGAN2 prior, Apache-2.0

★ 37,7 mil estrelas⑂ 6,3 mil forksApache-2.0atualizado jul 2024
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto

Dados do projeto

Repositório
TencentARC/GFPGAN
Estrelas no GitHub
37.703
Forks
6.279
Licença
Apache-2.0
Última atualização no GitHub
26 de julho de 2024
Categoria
Imagem
Tipo de ficha
Guia de instalação completo
Site oficial
Project page
// como funciona

Como funciona

  1. Clone the repo

    Download the source and move into the project folder.

  2. Install the dependencies

    Install BasicSR, facexlib and the requirements file, then install the package in development mode.

  3. Download a model

    Grab a pretrained model such as GFPGANv1.3.pth into experiments/pretrained_models.

  4. Restore your photos

    Point the inference script at a folder of images and collect the results.

// recursos

Por que as pessoas gostam tanto

Blind face restoration

Rebuilds faces from blurry, noisy or compressed photos using a pretrained StyleGAN2 prior.

Clean version, no CUDA extensions

Runs on Windows and CPU — no custom CUDA build step.

Three model versions to choose from

v1.3 for natural results, v1.4 for detail and identity, v1.2 for sharpness.

Background enhancement

Pairs with Real-ESRGAN to upscale the non-face parts of the photo too.

Training code included

The full training pipeline is in the repo if you want to improve it on your own data.

// execute você mesmo

Execute você mesmo

  1. Step 1 — Clone and install

    Clone the repo and install its Python dependencies.

    git clone https://github.com/TencentARC/GFPGAN.git
    cd GFPGAN
    pip install basicsr facexlib
    pip install -r requirements.txt
    python setup.py develop
  2. Step 2 — Download the v1.3 model

    Fetch the pretrained weights into the models folder.

    wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P experiments/pretrained_models
  3. Step 3 — Restore a folder of photos

    Run inference at 2x upscaling; results land in the results folder.

    python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2
// casos de uso

O que você pode criar

  • Restore old family photos with damaged faces
  • Clean up blurry profile pictures and scanned prints
  • Upscale low-quality faces for video frames
  • Pre-process faces before recognition or editing

Close neighbours on the Image shelf: Real-ESRGAN — practical blind super-resolution for real-world, and CodeFormer — NeurIPS 2022] Towards Robust Blind Face Restoration. The full shelf is the Image tools in the catalogue.

// perguntas frequentes

Perguntas frequentes

What does GFPGAN do?

It restores low-quality faces — blurry, compressed, noisy or old photos — using the facial knowledge inside a pretrained StyleGAN2.

Which model version should I use?

v1.3 for the most natural results, v1.4 for more detail and identity, v1.2 if you want sharper output. Try more than one on your photos.

Do I need a GPU?

No — the clean version runs on CPU and Windows without CUDA extensions, though a GPU is faster.

Is it free?

Yes — Apache 2.0.

Can it fix the background too?

Yes, with the Real-ESRGAN background upsampler (pip install realesrgan).

// continue explorando

Ferramentas semelhantes

Imagem

Real-ESRGAN

Real-ESRGAN — practical blind super-resolution for real-world photos and video: restores and upscales degraded images with models trained on pure synthetic data, BSD-3-Clause

★ 37,1 mil estrelasBSD-3-Clause
Ver o guia →
Imagem

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

★ 18,2 mil estrelasCustom (check repo)
Ver o guia →
Imagem

MirrorMetrics

Visual diagnostics for LoRA training — spot overfitting with face biometrics

★ 62 estrelasMIT
Ver o guia →
Imagem

ImageUpscaler

Simple Flask web app that upscales low-res images with AI

★ 129 estrelasMIT
Ver o guia →
Imagem

PhotoCraft

PhotoCraft — a clean-room Photoshop reimplementation in pure Rust: layers, masks, adjustment layers, type, vectors, brushes and real PSD files, offline, MIT / Apache-2.0

★ 73,2 mil estrelasMIT / Apache-2.0
Ver o guia →
Imagem

SAM 2

SAM 2 — Meta's Segment Anything Model 2: promptable segmentation for images and video, Apache-2.0

★ 20,1 mil estrelasApache-2.0
Ver o guia →
// alternativas

Alternativas em Imagem

Os outros projetos de Imagem com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se GFPGAN não for o ideal para você.

  • Stable Diffusion Webui★ 165,2 mil

    Stable Diffusion web UI

  • ComfyUI★ 136,0 mil

    The node-graph powerhouse for precise, professional AI image and video generation.

  • Immich★ 115,5 mil

    High performance self-hosted photo and video management solution

  • Stable Diffusion (Original)★ 73,6 mil

    The original latent text-to-image diffusion model from CompVis — the CVPR 2022 reference implementation, Open RAIL-M

  • PhotoCraft★ 73,2 mil

    PhotoCraft — a clean-room Photoshop reimplementation in pure Rust: layers, masks, adjustment layers, type, vectors, brushes and real PSD files, offline, MIT / Apache-2.0

// mais em image

Mais em Imagem

Projetos de Imagem próximos no catálogo, os mais próximos em estrelas de GFPGAN: continue explorando dos dois lados dele.

  • aseprite★ 39,9 mil

    Animated sprite editor & pixel art tool (Windows, macOS, Linux)

  • Real-ESRGAN★ 37,1 mil

    Real-ESRGAN — practical blind super-resolution for real-world photos and video: restores and upscales degraded images with models trained on pure synthetic data, BSD-3-Clause

  • PhotoPrism★ 40,3 mil

    AI-Powered Photos App 🌈💎✨

  • diffusers★ 34,6 mil

    🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

  • Upscayl★ 50,1 mil

    🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows

  • ControlNet★ 34,1 mil

    ControlNet — the original conditional control for diffusion models: steer Stable Diffusion with edges, depth, pose and scribbles instead of prompts alone, Apache-2.0

Baixe o GFPGAN

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.