{"id":17660935,"url":"https://github.com/soulteary/docker-gfpgan","last_synced_at":"2025-05-07T17:01:49.342Z","repository":{"id":148700430,"uuid":"494154984","full_name":"soulteary/docker-gfpgan","owner":"soulteary","description":"TencentARC GFPGAN ALL-IN-ONE Docker Images. support x86 / ARM.","archived":false,"fork":false,"pushed_at":"2023-08-08T15:54:41.000Z","size":1182,"stargazers_count":49,"open_issues_count":3,"forks_count":11,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T12:05:25.460Z","etag":null,"topics":["arm","docker","gfpgan","m1-mac","stable-diffusion-webui","x86"],"latest_commit_sha":null,"homepage":"https://soulteary.com/2022/05/20/use-docker-to-run-huggingface-models.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/soulteary.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-05-19T16:48:20.000Z","updated_at":"2025-03-26T01:43:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"70ce4b94-8669-46ac-b462-95a838f5921e","html_url":"https://github.com/soulteary/docker-gfpgan","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soulteary%2Fdocker-gfpgan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soulteary%2Fdocker-gfpgan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soulteary%2Fdocker-gfpgan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soulteary%2Fdocker-gfpgan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/soulteary","download_url":"https://codeload.github.com/soulteary/docker-gfpgan/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252921994,"owners_count":21825632,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arm","docker","gfpgan","m1-mac","stable-diffusion-webui","x86"],"created_at":"2024-10-23T17:09:45.978Z","updated_at":"2025-05-07T17:01:49.300Z","avatar_url":"https://github.com/soulteary.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Docker GFPGAN\n\n腾讯 ARC 实验室 GFPGAN Docker 运行方案。\n\n![](.github/compare.jpg)\n\n如果需要 CPU 运行，请参考第一篇教程，如果希望生产使用或 GPU 运行，请参考第二篇教程。\n\n## 项目预览\n\n第二篇教程相关：\n\n![](.github/first-look.jpg)\n\n![](.github/gfpgan-full-options.jpg)\n\n第一篇教程相关：\n\n![](.github/pictures.png)\n\n![](.github/preview.png)\n\n## 使用方法\n\n下载代码，执行脚本，构建镜像：\n\n```bash\ngit clone https://github.com/soulteary/docker-gfpgan.git\ncd docker-gfpgan\nbash scripts/build.sh\n```\n\n在完成基础镜像构建之后，可以从[网盘下载 models.zip](https://pan.baidu.com/s/1j6JyPEpCOM4D9NYUnPh0SQ?pwd=soul)。\n\n模型应用运行需要的所有模型都在这里了，下载完毕后，解压缩模型压缩包，将 gfpgan、model 两个目录放置到项目的根目录中，完整的项目结构是这样的：\n\n```bash\n├── docker\n├── gfpgan\n│   └── weights\n│       ├── detection_Resnet50_Final.pth\n│       └── parsing_parsenet.pth\n├── LICENSE\n├── model\n│   ├── GFPGANCleanv1-NoCE-C2.pth\n│   ├── GFPGANv1.2.pth\n│   ├── GFPGANv1.3.pth\n│   ├── GFPGANv1.4.pth\n│   ├── GFPGANv1.pth\n│   ├── README.md\n│   ├── RealESRGAN_x2plus.pth\n│   ├── realesr-general-x4v3.pth\n│   └── RestoreFormer.pth\n├── README.md\n├── scripts\n└── src\n```\n\n准备好模型文件之后，使用下面的命令启动模型应用：\n\n```bash\ndocker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --rm -it -v `pwd`/model:/app/model -v `pwd`/gfpgan:/app/gfpgan  -p 7860:7860 soulteary/docker-gfpgan\n```\n\n稍等片刻，我们将看到类似下面的日志：\n\n```bash\nRunning on local URL:  http://0.0.0.0:7860\n\nTo create a public link, set `share=True` in `launch()`.\n```\n\n接着，我们就可以打开浏览器访问 http://localhost:7860 或者 http://你的IP地址:7860 来试试看啦。\n\n## 相关教程\n\n- 《[Stable Diffusion 硬核生存指南：WebUI 中的 GFPGAN](https://soulteary.com/2023/08/04/stable-diffusion-hardcore-survival-guide-gfpgan-in-webui.html)》\n- 《[使用 Docker 来运行 HuggingFace 海量模型](https://soulteary.com/2022/05/20/use-docker-to-run-huggingface-models.html)》\n\n## 相关项目\n\n- https://github.com/TencentARC/GFPGAN\n- https://github.com/soulteary/docker-pytorch-playground\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoulteary%2Fdocker-gfpgan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsoulteary%2Fdocker-gfpgan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoulteary%2Fdocker-gfpgan/lists"}