[{"data":1,"prerenderedAt":245},["ShallowReactive",2],{"repo-danielgatis-rembg-zh-CN":3,"i18n-danielgatis-rembg-zh-CN":242},{"mirrorPool":4,"detail":13,"relatedProjects":170},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":26,"homepage":27,"pushedAt":28,"ownerAvatar":29,"ownerName":30,"ownerBio":27,"lastSyncTime":31,"lastReleaseTime":32,"tags":33,"license":37,"category":38,"subgroup":39,"releases":40},"danielgatis","rembg",286500101,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg",25156,"Python","Rembg is a tool to remove images background",{"Python":22,"Inno Setup":23,"Jupyter Notebook":24,"PowerShell":24,"Dockerfile":25},94.5,4.5,0.4,0.2,[],"","2026-10-21","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7380?v=4","Daniel Gatis","2026-10-22T12:59:42.561297+00:00","2026-10-21T21:17:52Z",[34,35,36],"background-removal","image-processing","python","MIT","tools","图像处理工具",[41,61,77,93,109,125,139,155],{"tag":42,"publishAt":32,"semVer":43,"prerelease":47,"assets":48},"v2.0.86",[44,45,46],2,0,86,false,[49,55],{"fileName":50,"sizeMb":51,"sha256":52,"downloadCount":53,"originUrl":54},"rembg-cli-cpu-installer.exe",114.25,"818a6219ea6fc4cbe4a6df54517f4080c9416a0e6b5f295f139c3fa5ef81a93c",11,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.86\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":57,"sha256":58,"downloadCount":59,"originUrl":60},"rembg-cli-gpu-installer.exe",248.9,"764cd7c70ab41b50ba6ab81a3c50252102190d45dd7c8898859e77bf0423c745",18,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.86\u002Frembg-cli-gpu-installer.exe",{"tag":62,"publishAt":63,"semVer":64,"prerelease":47,"assets":66},"v2.0.85","2026-09-20T17:16:22Z",[44,45,65],85,[67,72],{"fileName":50,"sizeMb":68,"sha256":69,"downloadCount":70,"originUrl":71},113.78,"7099a98ada1c5706230e848576ac659ac875b360988928148e824fed464a637f",786,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.85\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":73,"sha256":74,"downloadCount":75,"originUrl":76},242.05,"4eb6c34e8c06663dd8edb9078ce1770870b9e559c2a0bc1bda604305b7da35e1",806,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.85\u002Frembg-cli-gpu-installer.exe",{"tag":78,"publishAt":79,"semVer":80,"prerelease":47,"assets":82},"v2.0.84","2026-09-08T01:03:19Z",[44,45,81],84,[83,88],{"fileName":50,"sizeMb":84,"sha256":85,"downloadCount":86,"originUrl":87},113.51,"f3f12704cad3616899eaf56fc9edb42497ede4f785d6a559bb7203340d300786",359,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.84\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":89,"sha256":90,"downloadCount":91,"originUrl":92},230.49,"20a7934901b374e5e3a30006441c7ace23fee7de85a7947594343ad6120beead",287,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.84\u002Frembg-cli-gpu-installer.exe",{"tag":94,"publishAt":95,"semVer":96,"prerelease":47,"assets":98},"v2.0.83","2026-09-02T13:03:57Z",[44,45,97],83,[99,104],{"fileName":50,"sizeMb":100,"sha256":101,"downloadCount":102,"originUrl":103},113.47,"cbb690503408863e1f84c6d8b827ffc48258fb39a0099d00b12044ca1875c7ba",145,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.83\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":105,"sha256":106,"downloadCount":107,"originUrl":108},230.43,"6ab34f25636382229749d983723f96211fe18cdb562100b094bb65266db73552",137,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.83\u002Frembg-cli-gpu-installer.exe",{"tag":110,"publishAt":111,"semVer":112,"prerelease":47,"assets":114},"v2.0.82","2026-09-02T12:57:08Z",[44,45,113],82,[115,120],{"fileName":50,"sizeMb":116,"sha256":117,"downloadCount":118,"originUrl":119},113.46,"452077114525bec41517c18677ea9a3f545322b2b62edf6171ce689a3de567f7",8,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.82\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":121,"sha256":122,"downloadCount":123,"originUrl":124},230.44,"9948e78afc309f8c375e9719cab60a2d38b58ac1942760caffaa23c46558afbc",9,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.82\u002Frembg-cli-gpu-installer.exe",{"tag":126,"publishAt":127,"semVer":128,"prerelease":47,"assets":130},"v2.0.81","2026-08-18T23:41:55Z",[44,45,129],81,[131,135],{"fileName":50,"sizeMb":100,"sha256":132,"downloadCount":133,"originUrl":134},"a47c90d105ab4e5120d09d1f317e615e5cca8877730a020b4bc6899cab640976",304,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.81\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":121,"sha256":136,"downloadCount":137,"originUrl":138},"9e989971cd12f3973a3c73125a4aefc2fbf6488003252510af1702f83aafc794",367,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.81\u002Frembg-cli-gpu-installer.exe",{"tag":140,"publishAt":141,"semVer":142,"prerelease":47,"assets":144},"v2.0.80","2026-08-17T04:56:35Z",[44,45,143],80,[145,150],{"fileName":50,"sizeMb":146,"sha256":147,"downloadCount":148,"originUrl":149},113.3,"9a53b0f5415d153dfd64f022b3731d02b9e4e87bc0093ef96682e7ead895f52b",61,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.80\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":151,"sha256":152,"downloadCount":153,"originUrl":154},316.92,"96417ac50d3badd4284dd4b386ff9ad501c18d667811a695547c8628afde188b",52,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.80\u002Frembg-cli-gpu-installer.exe",{"tag":156,"publishAt":157,"semVer":158,"prerelease":47,"assets":160},"v2.0.79","2026-08-17T02:48:23Z",[44,45,159],79,[161,166],{"fileName":50,"sizeMb":162,"sha256":163,"downloadCount":164,"originUrl":165},113.27,"00e1a2519dac4054cea2ad74662d09274cbc8ce2d932c4f42f350d90ac60738b",13,"https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.79\u002Frembg-cli-cpu-installer.exe",{"fileName":56,"sizeMb":167,"sha256":168,"downloadCount":123,"originUrl":169},316.91,"ac5bbebaad60b23bda1b02956b86bf512cf4b911d69f1280da07c58002f10d46","https:\u002F\u002Fgithub.com\u002Fdanielgatis\u002Frembg\u002Freleases\u002Fdownload\u002Fv2.0.79\u002Frembg-cli-gpu-installer.exe",[171,193,206,217,225,234],{"owner":172,"repo":172,"repoId":173,"category":38,"subgroup":39,"language":174,"tags":175,"starCount":183,"ownerUid":184,"latestTag":185,"platforms":186,"lastReleaseTime":190,"downloadCount":191,"description":192},"ImageMagick",35780977,"C",[176,177,178,179,35,180,181,182],"command-line-image-tool","digital-image-editing","image-conversion","image-manipulation","imagemagick","mastering-digital-image-alchemy","open-source-software",17664,12486768,"7.1.2-34",[187,188,189],"windows","linux","other","2026-10-14T20:45:10Z",7421,"ImageMagick 是一个开源的图像处理软件套件，提供命令行工具与多语言接口，可在 Linux、Windows、macOS 上完成图片的创建、编辑、合成与格式转换。",{"owner":194,"repo":195,"repoId":196,"category":38,"subgroup":39,"language":174,"tags":197,"starCount":198,"ownerUid":199,"latestTag":200,"platforms":201,"lastReleaseTime":203,"downloadCount":204,"description":205},"darktable-org","darktable",3791835,[],13189,1561544,"nightly",[187,202,188],"mac","2026-10-04T01:29:08Z",77,"darktable 是一款开源的摄影工作流与 RAW 显影软件，负责照片的导入、显影、修饰与组织管理，可在 Linux、Windows、macOS 上运行。",{"owner":207,"repo":208,"repoId":209,"category":38,"subgroup":39,"language":210,"tags":211,"starCount":212,"ownerUid":213,"latestTag":27,"platforms":214,"distribution":215,"lastReleaseTime":27,"downloadCount":45,"description":216},"KDE","krita",43975673,"C++",[],10654,14312869,[],"official-site","Krita 是一款开源的数字绘画软件，面向插画、漫画与概念设计，提供完整的笔刷引擎与绘画工具，可在 Windows、macOS、Linux 上运行。",{"owner":218,"repo":218,"repoId":219,"category":38,"subgroup":39,"language":27,"tags":220,"starCount":221,"ownerUid":222,"latestTag":27,"platforms":223,"distribution":215,"lastReleaseTime":27,"downloadCount":45,"description":224},"photopea",46613660,[],8513,15955558,[],"photopea\u002Fphotopea 是 Photopea 在线图片编辑器的官方反馈仓库，用于收集缺陷与建议，本身不含编辑器源码，软件在浏览器中直接使用。",{"owner":226,"repo":227,"repoId":228,"category":38,"subgroup":39,"language":174,"tags":229,"starCount":230,"ownerUid":231,"latestTag":27,"platforms":232,"distribution":215,"lastReleaseTime":27,"downloadCount":45,"description":233},"GNOME","gimp",4537508,[],6551,1801039,[],"GIMP 是一款开源免费的图像处理软件，用于照片修饰、图像合成与图片创作，提供图层、蒙版、选区与插件体系，可在 Linux、Windows、macOS 上运行。",{"owner":235,"repo":235,"repoId":236,"category":38,"subgroup":39,"language":27,"tags":237,"starCount":238,"ownerUid":239,"latestTag":27,"platforms":240,"distribution":215,"lastReleaseTime":27,"downloadCount":45,"description":241},"inkscape",23163093,[],4066,8506907,[],"Inkscape 是一款开源矢量绘图软件；本仓库是项目的入口说明页，只含说明文档与一张图片，源码与安装包均需从官方渠道获取。",{"description":243,"readmeHtml":244},"rembg 是基于 AI 模型的图片背景移除工具，提供命令行、Python 库、HTTP 服务和 Docker 四种使用方式，模型本地推理即可把主体抠出成透明背景。","\u003Ch2 id=\"项目概述\">项目概述\u003C\u002Fh2>\u003Cp>rembg 是一个移除图片背景的工具，通过内置的 U2Net 等 AI 模型把前景主体从背景中分离出来。它既能当命令行工具用，也能作为 Python 库、HTTP 服务器或 Docker 容器运行，模型在本地推理，图片不必上传第三方服务。\u003C\u002Fp>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>项目\u003C\u002Fth>\n\u003Cth>内容\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>平台\u003C\u002Ftd>\n\u003Ctd>Linux、macOS、Windows、Docker\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>语言\u003C\u002Ftd>\n\u003Ctd>Python 3.11 至 3.13\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>许可\u003C\u002Ftd>\n\u003Ctd>MIT\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>推理引擎\u003C\u002Ftd>\n\u003Ctd>ONNX Runtime\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Cblockquote>\n\u003Cp>本地 AI 抠图，一条命令把主体从背景里拿出来。\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2 id=\"主要功能\">主要功能\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>一键去背景\u003C\u002Fstrong>：输入任意图片，自动识别主体并输出透明背景结果\u003C\u002Fli>\n\u003Cli>\u003Cstrong>多种使用形态\u003C\u002Fstrong>：命令行、Python 库、HTTP 服务、Docker 容器均可运行\u003C\u002Fli>\n\u003Cli>\u003Cstrong>多模型可选\u003C\u002Fstrong>：内置 u2net、isnet 等模型，可按人像、物体等场景切换\u003C\u002Fli>\n\u003Cli>\u003Cstrong>CPU 与 GPU\u003C\u002Fstrong>：默认 CPU 推理，NVIDIA 显卡可切换 onnxruntime-gpu 加速\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Alpha Matting\u003C\u002Fstrong>：开启边缘优化参数，让发丝等细节过渡更自然\u003C\u002Fli>\n\u003Cli>\u003Cstrong>批量处理\u003C\u002Fstrong>：命令行可对整个目录的图片批量去背景\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"适用人群\">适用人群\u003C\u002Fh2>\u003Cul>\n\u003Cli>电商与素材制作人员\u003C\u002Fli>\n\u003Cli>批量处理图片的内容团队\u003C\u002Fli>\n\u003Cli>需要集成抠图能力的应用开发者\u003C\u002Fli>\n\u003Cli>要求本地处理、注重隐私的设计师\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"快速上手\">快速上手\u003C\u002Fh2>\u003Col>\n\u003Cli>按硬件选择后端安装\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">pip install 'rembg[cpu,cli]'\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"2\">\n\u003Cli>用命令行处理单张图片\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">rembg i input.png output.png\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"3\">\n\u003Cli>或在代码中调用\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-python\">from rembg import remove\nfrom PIL import Image\n\ninp = Image.open('input.png')\nremove(inp).save('output.png')\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Ch2 id=\"核心优势\">核心优势\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>本地推理\u003C\u002Fstrong>：模型在本机运行，图片不出内网\u003C\u002Fli>\n\u003Cli>\u003Cstrong>形态灵活\u003C\u002Fstrong>：从个人脚本到服务化部署，同一套能力多端复用\u003C\u002Fli>\n\u003Cli>\u003Cstrong>开箱即用\u003C\u002Fstrong>：首次运行自动下载模型，无需手工配置环境\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"系统要求\">系统要求\u003C\u002Fh2>\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>项目\u003C\u002Fth>\n\u003Cth>要求\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>语言\u003C\u002Ftd>\n\u003Ctd>Python 3.11 及以上、3.14 以下\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>操作系统\u003C\u002Ftd>\n\u003Ctd>Linux、macOS、Windows\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>硬件\u003C\u002Ftd>\n\u003Ctd>CPU 即可运行；NVIDIA 显卡可启用 GPU 加速\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"注意事项\">注意事项\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>首次运行需下载模型\u003C\u002Fstrong>：模型文件较大，网络不佳时可提前手动放置到缓存目录\u003C\u002Fli>\n\u003Cli>\u003Cstrong>效果因图而异\u003C\u002Fstrong>：主体与背景颜色相近或边缘复杂的图片，建议尝试不同模型或开启 alpha matting\u003C\u002Fli>\n\u003C\u002Ful>\n",1793197842283]