<p align="center">
<img src="assets/gfpgan_logo.png" height=130>
</p>
## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
<div align="center">
<!-- <a href="https://twitter.com/_Xintao_" style="text-decoration:none;">
<img src="https://user-images.githubusercontent.com/17445847/187162058-c764ced6-952f-404b-ac85-ba95cce18e7b.png" width="4%" alt="" />
</a> -->
[](https://github.com/TencentARC/GFPGAN/releases)
[](https://pypi.org/project/gfpgan/)
[](https://github.com/TencentARC/GFPGAN/issues)
[](https://github.com/TencentARC/GFPGAN/issues)
[](https://github.com/TencentARC/GFPGAN/blob/master/LICENSE)
[](https://github.com/TencentARC/GFPGAN/blob/master/.github/workflows/pylint.yml)
[](https://github.com/TencentARC/GFPGAN/blob/master/.github/workflows/publish-pip.yml)
</div>
1. :boom: **Updated** online demo: [](https://replicate.com/tencentarc/gfpgan). Here is the [backup](https://replicate.com/xinntao/gfpgan).
1. :boom: **Updated** online demo: [](https://huggingface.co/spaces/Xintao/GFPGAN)
1. [Colab Demo](https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo) for GFPGAN <a href="https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>; (Another [Colab Demo](https://colab.research.google.com/drive/1Oa1WwKB4M4l1GmR7CtswDVgOCOeSLChA?usp=sharing) for the original paper model)
<!-- 3. Online demo: [Replicate.ai](https://replicate.com/xinntao/gfpgan) (may need to sign in, return the whole image)
4. Online demo: [Baseten.co](https://app.baseten.co/applications/Q04Lz0d/operator_views/8qZG6Bg) (backed by GPU, returns the whole image)
5. We provide a *clean* version of GFPGAN, which can run without CUDA extensions. So that it can run in **Windows** or on **CPU mode**. -->
> :rocket: **Thanks for your interest in our work. You may also want to check our new updates on the *tiny models* for *anime images and videos* in [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN/blob/master/docs/anime_video_model.md)** :blush:
GFPGAN aims at developing a **Practical Algorithm for Real-world Face Restoration**.<br>
It leverages rich and diverse priors encapsulated in a pretrained face GAN (*e.g.*, StyleGAN2) for blind face restoration.
:question: Frequently Asked Questions can be found in [FAQ.md](FAQ.md).
:triangular_flag_on_post: **Updates**
- :white_check_mark: Add [RestoreFormer](https://github.com/wzhouxiff/RestoreFormer) inference codes.
- :white_check_mark: Add [V1.4 model](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth), which produces slightly more details and better identity than V1.3.
- :white_check_mark: Add **[V1.3 model](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth)**, which produces **more natural** restoration results, and better results on *very low-quality* / *high-quality* inputs. See more in [Model zoo](#european_castle-model-zoo), [Comparisons.md](Comparisons.md)
- :white_check_mark: Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/GFPGAN).
- :white_check_mark: Support enhancing non-face regions (background) with [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN).
- :white_check_mark: We provide a *clean* version of GFPGAN, which does not require CUDA extensions.
- :white_check_mark: We provide an updated model without colorizing faces.
---
If GFPGAN is helpful in your photos/projects, please help to :star: this repo or recommend it to your friends. Thanks:blush:
Other recommended projects:<br>
:arrow_forward: [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration<br>
:arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>
:arrow_forward: [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions<br>
:arrow_forward: [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison<br>
---
### :book: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior
> [[Paper](https://arxiv.org/abs/2101.04061)]   [[Project Page](https://xinntao.github.io/projects/gfpgan)]   [Demo] <br>
> [Xintao Wang](https://xinntao.github.io/), [Yu Li](https://yu-li.github.io/), [Honglun Zhang](https://scholar.google.com/citations?hl=en&user=KjQLROoAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>
> Applied Research Center (ARC), Tencent PCG
<p align="center">
<img src="https://xinntao.github.io/projects/GFPGAN_src/gfpgan_teaser.jpg">
</p>
---
## :wrench: Dependencies and Installation
- Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
- [PyTorch >= 1.7](https://pytorch.org/)
- Option: NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)
- Option: Linux
### Installation
We now provide a *clean* version of GFPGAN, which does not require customized CUDA extensions. <br>
If you want to use the original model in our paper, please see [PaperModel.md](PaperModel.md) for installation.
1. Clone repo
```bash
git clone https://github.com/TencentARC/GFPGAN.git
cd GFPGAN
```
1. Install dependent packages
```bash
# Install basicsr - https://github.com/xinntao/BasicSR
# We use BasicSR for both training and inference
pip install basicsr
# Install facexlib - https://github.com/xinntao/facexlib
# We use face detection and face restoration helper in the facexlib package
pip install facexlib
pip install -r requirements.txt
python setup.py develop
# If you want to enhance the background (non-face) regions with Real-ESRGAN,
# you also need to install the realesrgan package
pip install realesrgan
```
## :zap: Quick Inference
We take the v1.3 version for an example. More models can be found [here](#european_castle-model-zoo).
Download pre-trained models: [GFPGANv1.3.pth](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth)
```bash
wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P experiments/pretrained_models
```
**Inference!**
```bash
python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2
```
```console
Usage: python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2 [options]...
-h show this help
-i input Input image or folder. Default: inputs/whole_imgs
-o output Output folder. Default: results
-v version GFPGAN model version. Option: 1 | 1.2 | 1.3. Default: 1.3
-s upscale The final upsampling scale of the image. Default: 2
-bg_upsampler background upsampler. Default: realesrgan
-bg_tile Tile size for background sampler, 0 for no tile during testing. Default: 400
-suffix Suffix of the restored faces
-only_center_face Only restore the center face
-aligned Input are aligned faces
-ext Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto
```
If you want to use the original model in our paper, please see [PaperModel.md](PaperModel.md) for installation and inference.
## :european_castle: Model Zoo
| Version | Model Name | Description |
| :---: | :---: | :---: |
| V1.3 | [GFPGANv1.3.pth](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) | Based on V1.2; **more natural** restoration results; better results on very low-quality / high-quality inputs. |
| V1.2 | [GFPGANCleanv1-NoCE-C2.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth) | No colorization; no CUDA extensions are required. Trained with more data with pre-processing. |
| V1 | [GFPGANv1.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/GFPGANv1.pth) | The paper model, with colorization. |
The comparisons are in [Comparisons.md](Comparisons.md).
Note that V1.3 is not always better than V1.2. You may need to select different models based on your purpose and inputs.
| Version | Strengths | Weaknesses |
| :---: | :---: | :---: |
|V1.3 | ✓ natural outputs<br> ✓better results on very low-quality inputs <br> ✓ work on relatively high-quality inputs <br>✓ can have repeated (twice) restorations | ✗ not very sharp <br> ✗ have a slight change on identity |
|V1.2 | ✓ sharper output <br> ✓ with beauty makeup | ✗ some outputs are unnatural |
You can find **more models (such as the discriminators)** here: [[Google Drive](https://drive.google.com/drive/folders/17rLiFzcUMoQuhLnptDsKolegHWwJOnHu?usp=sharing)], OR [[Tencent Cloud 腾讯微云](https://share.weiyun.com/ShYoCCoc)]
## :computer: Training
We provide the training codes for GFPGAN (used in our paper). <br>
You could improve it according to your own needs.
**Tips**
1. More high quality faces can improve the restoration quality.
2. You may need to perform some pre-processing, such as beauty makeup.
**Procedures**
(You can try a simple version ( `options/train_gfpgan_v1_simple.yml`) that does not require face component landmarks.)
1. Dataset preparation: [FFHQ](https://github.com/NVlabs/ffhq-dataset)
1. Download pre-trained models and other data. Put them in the `experiments/pretrained_models` folder.
1. [Pre-trained StyleGAN2 model: StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth)
1. [Component locations of FFHQ: FFHQ_eye_mouth_landmarks_512.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/FFHQ_eye_mouth_landmarks_512.pth)
1. [A simple ArcFace model: arcface_resnet18.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/arcface_resnet18.pth)
1. Modify the configuration file `options/train_gfpgan_v1.yml` accordingly.
1. Training
> python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 gfpgan/train.py -opt options/train_gfpgan_v1.yml --launcher pytorch
## :scroll: License and Acknowledgement
GFPGAN is released under Apache License Version 2.0.
## BibTeX
@InProceedings{wang2021gfpgan,
author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan},
title = {Towards Real-World Blind Face Restoration with Generative Facial Prior},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}
## :e-mail: Contact
If you have any question, please email `xintao.wang@outlook.com` or `xintaowang@tencent.com`.
Raw data
{
"_id": null,
"home_page": "https://github.com/TencentARC/GFPGAN",
"name": "new-gfpgan",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "computer vision, pytorch, image restoration, super-resolution, face restoration, gan, gfpgan",
"author": "Xintao Wang",
"author_email": "xintao.wang@outlook.com",
"download_url": "https://files.pythonhosted.org/packages/fc/a9/6afb5bafa5f1cb8f7e2ce89125135ccab983e103fe3717bd7c0d36977996/new-gfpgan-1.0.1.tar.gz",
"platform": null,
"description": "<p align=\"center\">\r\n <img src=\"assets/gfpgan_logo.png\" height=130>\r\n</p>\r\n\r\n## <div align=\"center\"><b><a href=\"README.md\">English</a> | <a href=\"README_CN.md\">\u7b80\u4f53\u4e2d\u6587</a></b></div>\r\n\r\n<div align=\"center\">\r\n<!-- <a href=\"https://twitter.com/_Xintao_\" style=\"text-decoration:none;\">\r\n <img src=\"https://user-images.githubusercontent.com/17445847/187162058-c764ced6-952f-404b-ac85-ba95cce18e7b.png\" width=\"4%\" alt=\"\" />\r\n</a> -->\r\n\r\n[](https://github.com/TencentARC/GFPGAN/releases)\r\n[](https://pypi.org/project/gfpgan/)\r\n[](https://github.com/TencentARC/GFPGAN/issues)\r\n[](https://github.com/TencentARC/GFPGAN/issues)\r\n[](https://github.com/TencentARC/GFPGAN/blob/master/LICENSE)\r\n[](https://github.com/TencentARC/GFPGAN/blob/master/.github/workflows/pylint.yml)\r\n[](https://github.com/TencentARC/GFPGAN/blob/master/.github/workflows/publish-pip.yml)\r\n</div>\r\n\r\n1. :boom: **Updated** online demo: [](https://replicate.com/tencentarc/gfpgan). Here is the [backup](https://replicate.com/xinntao/gfpgan).\r\n1. :boom: **Updated** online demo: [](https://huggingface.co/spaces/Xintao/GFPGAN)\r\n1. [Colab Demo](https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo) for GFPGAN <a href=\"https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"google colab logo\"></a>; (Another [Colab Demo](https://colab.research.google.com/drive/1Oa1WwKB4M4l1GmR7CtswDVgOCOeSLChA?usp=sharing) for the original paper model)\r\n\r\n<!-- 3. Online demo: [Replicate.ai](https://replicate.com/xinntao/gfpgan) (may need to sign in, return the whole image)\r\n4. Online demo: [Baseten.co](https://app.baseten.co/applications/Q04Lz0d/operator_views/8qZG6Bg) (backed by GPU, returns the whole image)\r\n5. We provide a *clean* version of GFPGAN, which can run without CUDA extensions. So that it can run in **Windows** or on **CPU mode**. -->\r\n\r\n> :rocket: **Thanks for your interest in our work. You may also want to check our new updates on the *tiny models* for *anime images and videos* in [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN/blob/master/docs/anime_video_model.md)** :blush:\r\n\r\nGFPGAN aims at developing a **Practical Algorithm for Real-world Face Restoration**.<br>\r\nIt leverages rich and diverse priors encapsulated in a pretrained face GAN (*e.g.*, StyleGAN2) for blind face restoration.\r\n\r\n:question: Frequently Asked Questions can be found in [FAQ.md](FAQ.md).\r\n\r\n:triangular_flag_on_post: **Updates**\r\n\r\n- :white_check_mark: Add [RestoreFormer](https://github.com/wzhouxiff/RestoreFormer) inference codes.\r\n- :white_check_mark: Add [V1.4 model](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth), which produces slightly more details and better identity than V1.3.\r\n- :white_check_mark: Add **[V1.3 model](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth)**, which produces **more natural** restoration results, and better results on *very low-quality* / *high-quality* inputs. See more in [Model zoo](#european_castle-model-zoo), [Comparisons.md](Comparisons.md)\r\n- :white_check_mark: Integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See [Gradio Web Demo](https://huggingface.co/spaces/akhaliq/GFPGAN).\r\n- :white_check_mark: Support enhancing non-face regions (background) with [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN).\r\n- :white_check_mark: We provide a *clean* version of GFPGAN, which does not require CUDA extensions.\r\n- :white_check_mark: We provide an updated model without colorizing faces.\r\n\r\n---\r\n\r\nIf GFPGAN is helpful in your photos/projects, please help to :star: this repo or recommend it to your friends. Thanks:blush:\r\nOther recommended projects:<br>\r\n:arrow_forward: [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration<br>\r\n:arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>\r\n:arrow_forward: [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions<br>\r\n:arrow_forward: [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison<br>\r\n\r\n---\r\n\r\n### :book: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior\r\n\r\n> [[Paper](https://arxiv.org/abs/2101.04061)]   [[Project Page](https://xinntao.github.io/projects/gfpgan)]   [Demo] <br>\r\n> [Xintao Wang](https://xinntao.github.io/), [Yu Li](https://yu-li.github.io/), [Honglun Zhang](https://scholar.google.com/citations?hl=en&user=KjQLROoAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>\r\n> Applied Research Center (ARC), Tencent PCG\r\n\r\n<p align=\"center\">\r\n <img src=\"https://xinntao.github.io/projects/GFPGAN_src/gfpgan_teaser.jpg\">\r\n</p>\r\n\r\n---\r\n\r\n## :wrench: Dependencies and Installation\r\n\r\n- Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))\r\n- [PyTorch >= 1.7](https://pytorch.org/)\r\n- Option: NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)\r\n- Option: Linux\r\n\r\n### Installation\r\n\r\nWe now provide a *clean* version of GFPGAN, which does not require customized CUDA extensions. <br>\r\nIf you want to use the original model in our paper, please see [PaperModel.md](PaperModel.md) for installation.\r\n\r\n1. Clone repo\r\n\r\n ```bash\r\n git clone https://github.com/TencentARC/GFPGAN.git\r\n cd GFPGAN\r\n ```\r\n\r\n1. Install dependent packages\r\n\r\n ```bash\r\n # Install basicsr - https://github.com/xinntao/BasicSR\r\n # We use BasicSR for both training and inference\r\n pip install basicsr\r\n\r\n # Install facexlib - https://github.com/xinntao/facexlib\r\n # We use face detection and face restoration helper in the facexlib package\r\n pip install facexlib\r\n\r\n pip install -r requirements.txt\r\n python setup.py develop\r\n\r\n # If you want to enhance the background (non-face) regions with Real-ESRGAN,\r\n # you also need to install the realesrgan package\r\n pip install realesrgan\r\n ```\r\n\r\n## :zap: Quick Inference\r\n\r\nWe take the v1.3 version for an example. More models can be found [here](#european_castle-model-zoo).\r\n\r\nDownload pre-trained models: [GFPGANv1.3.pth](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth)\r\n\r\n```bash\r\nwget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P experiments/pretrained_models\r\n```\r\n\r\n**Inference!**\r\n\r\n```bash\r\npython inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2\r\n```\r\n\r\n```console\r\nUsage: python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2 [options]...\r\n\r\n -h show this help\r\n -i input Input image or folder. Default: inputs/whole_imgs\r\n -o output Output folder. Default: results\r\n -v version GFPGAN model version. Option: 1 | 1.2 | 1.3. Default: 1.3\r\n -s upscale The final upsampling scale of the image. Default: 2\r\n -bg_upsampler background upsampler. Default: realesrgan\r\n -bg_tile Tile size for background sampler, 0 for no tile during testing. Default: 400\r\n -suffix Suffix of the restored faces\r\n -only_center_face Only restore the center face\r\n -aligned Input are aligned faces\r\n -ext Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto\r\n```\r\n\r\nIf you want to use the original model in our paper, please see [PaperModel.md](PaperModel.md) for installation and inference.\r\n\r\n## :european_castle: Model Zoo\r\n\r\n| Version | Model Name | Description |\r\n| :---: | :---: | :---: |\r\n| V1.3 | [GFPGANv1.3.pth](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) | Based on V1.2; **more natural** restoration results; better results on very low-quality / high-quality inputs. |\r\n| V1.2 | [GFPGANCleanv1-NoCE-C2.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth) | No colorization; no CUDA extensions are required. Trained with more data with pre-processing. |\r\n| V1 | [GFPGANv1.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/GFPGANv1.pth) | The paper model, with colorization. |\r\n\r\nThe comparisons are in [Comparisons.md](Comparisons.md).\r\n\r\nNote that V1.3 is not always better than V1.2. You may need to select different models based on your purpose and inputs.\r\n\r\n| Version | Strengths | Weaknesses |\r\n| :---: | :---: | :---: |\r\n|V1.3 | \u2713 natural outputs<br> \u2713better results on very low-quality inputs <br> \u2713 work on relatively high-quality inputs <br>\u2713 can have repeated (twice) restorations | \u2717 not very sharp <br> \u2717 have a slight change on identity |\r\n|V1.2 | \u2713 sharper output <br> \u2713 with beauty makeup | \u2717 some outputs are unnatural |\r\n\r\nYou can find **more models (such as the discriminators)** here: [[Google Drive](https://drive.google.com/drive/folders/17rLiFzcUMoQuhLnptDsKolegHWwJOnHu?usp=sharing)], OR [[Tencent Cloud \u817e\u8baf\u5fae\u4e91](https://share.weiyun.com/ShYoCCoc)]\r\n\r\n## :computer: Training\r\n\r\nWe provide the training codes for GFPGAN (used in our paper). <br>\r\nYou could improve it according to your own needs.\r\n\r\n**Tips**\r\n\r\n1. More high quality faces can improve the restoration quality.\r\n2. You may need to perform some pre-processing, such as beauty makeup.\r\n\r\n**Procedures**\r\n\r\n(You can try a simple version ( `options/train_gfpgan_v1_simple.yml`) that does not require face component landmarks.)\r\n\r\n1. Dataset preparation: [FFHQ](https://github.com/NVlabs/ffhq-dataset)\r\n\r\n1. Download pre-trained models and other data. Put them in the `experiments/pretrained_models` folder.\r\n 1. [Pre-trained StyleGAN2 model: StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth)\r\n 1. [Component locations of FFHQ: FFHQ_eye_mouth_landmarks_512.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/FFHQ_eye_mouth_landmarks_512.pth)\r\n 1. [A simple ArcFace model: arcface_resnet18.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/arcface_resnet18.pth)\r\n\r\n1. Modify the configuration file `options/train_gfpgan_v1.yml` accordingly.\r\n\r\n1. Training\r\n\r\n> python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 gfpgan/train.py -opt options/train_gfpgan_v1.yml --launcher pytorch\r\n\r\n## :scroll: License and Acknowledgement\r\n\r\nGFPGAN is released under Apache License Version 2.0.\r\n\r\n## BibTeX\r\n\r\n @InProceedings{wang2021gfpgan,\r\n author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan},\r\n title = {Towards Real-World Blind Face Restoration with Generative Facial Prior},\r\n booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\r\n year = {2021}\r\n }\r\n\r\n## :e-mail: Contact\r\n\r\nIf you have any question, please email `xintao.wang@outlook.com` or `xintaowang@tencent.com`.\r\n",
"bugtrack_url": null,
"license": "Apache License Version 2.0",
"summary": "GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration",
"version": "1.0.1",
"project_urls": {
"Homepage": "https://github.com/TencentARC/GFPGAN"
},
"split_keywords": [
"computer vision",
" pytorch",
" image restoration",
" super-resolution",
" face restoration",
" gan",
" gfpgan"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a31332ad47e84ee2f3e90ac29e3294dd433e7108e0549765a899d76e26acc54c",
"md5": "7e93a2513c9a4d222e124ec3c7985be1",
"sha256": "98325f70d58ecb6f6253d20ef068942713ada0b2afdba18c6de050b0ac95a29c"
},
"downloads": -1,
"filename": "new_gfpgan-1.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7e93a2513c9a4d222e124ec3c7985be1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 52321,
"upload_time": "2024-05-26T05:27:59",
"upload_time_iso_8601": "2024-05-26T05:27:59.130107Z",
"url": "https://files.pythonhosted.org/packages/a3/13/32ad47e84ee2f3e90ac29e3294dd433e7108e0549765a899d76e26acc54c/new_gfpgan-1.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fca96afb5bafa5f1cb8f7e2ce89125135ccab983e103fe3717bd7c0d36977996",
"md5": "cd30f81ab2da47af936b40b5787f222d",
"sha256": "2d73fe7b80cbd90866ab9836ea6aac9b98ce119fdbbbfe1127b9ad4d0fa60073"
},
"downloads": -1,
"filename": "new-gfpgan-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "cd30f81ab2da47af936b40b5787f222d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 99446,
"upload_time": "2024-05-26T05:28:02",
"upload_time_iso_8601": "2024-05-26T05:28:02.841069Z",
"url": "https://files.pythonhosted.org/packages/fc/a9/6afb5bafa5f1cb8f7e2ce89125135ccab983e103fe3717bd7c0d36977996/new-gfpgan-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-26 05:28:02",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "TencentARC",
"github_project": "GFPGAN",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "basicsr",
"specs": [
[
">=",
"1.4.2"
]
]
},
{
"name": "facexlib",
"specs": [
[
">=",
"0.2.5"
]
]
},
{
"name": "lmdb",
"specs": []
},
{
"name": "numpy",
"specs": []
},
{
"name": "opencv-python",
"specs": []
},
{
"name": "pyyaml",
"specs": []
},
{
"name": "scipy",
"specs": []
},
{
"name": "tb-nightly",
"specs": []
},
{
"name": "torch",
"specs": [
[
">=",
"1.7"
]
]
},
{
"name": "torchvision",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "yapf",
"specs": []
}
],
"lcname": "new-gfpgan"
}
JSON
