{"id":17011757,"url":"https://github.com/flaribbit/imgfind","last_synced_at":"2025-07-26T02:34:06.083Z","repository":{"id":195148832,"uuid":"692074056","full_name":"flaribbit/imgfind","owner":"flaribbit","description":"根据文本描述搜索本地图片的工具，powered by Rust + candle + CLIP","archived":false,"fork":false,"pushed_at":"2023-10-31T08:35:14.000Z","size":3603,"stargazers_count":145,"open_issues_count":2,"forks_count":6,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-08T13:51:43.147Z","etag":null,"topics":["clip-model","image-processing","image-recognition","image-search-engine","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flaribbit.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-09-15T13:56:23.000Z","updated_at":"2024-11-18T09:07:05.000Z","dependencies_parsed_at":"2023-10-15T22:53:37.202Z","dependency_job_id":"5cbbd694-7f61-4318-aff9-776aa0436e44","html_url":"https://github.com/flaribbit/imgfind","commit_stats":null,"previous_names":["flaribbit/imgfind"],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flaribbit%2Fimgfind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flaribbit%2Fimgfind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flaribbit%2Fimgfind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flaribbit%2Fimgfind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flaribbit","download_url":"https://codeload.github.com/flaribbit/imgfind/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243858929,"owners_count":20359260,"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":["clip-model","image-processing","image-recognition","image-search-engine","machine-learning"],"created_at":"2024-10-14T06:07:56.591Z","updated_at":"2025-03-17T09:31:09.293Z","avatar_url":"https://github.com/flaribbit.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 基于 CLIP 的本地图片搜索工具\n\n![image](https://github.com/flaribbit/imgfind/assets/24885181/f5ac6334-b59a-4a60-a77b-65f23c57c1c2)\n\n[English version](#local-image-search-tool-based-on-clip)\n\n## 安装\n\nwindows 推荐使用 scoop 一键安装\n\n```\nscoop install https://raw.githubusercontent.com/flaribbit/imgfind/master/scoop/imgfind.json\n```\n\nandroid 可以使用 termux 下载最新 release 运行，其他系统目前只能自己编译。\n\n## 使用方法\n\n1. 为目录中的所有图片文件创建 embeddings，以便搜索：\n```bash\n./imgfind add 目录\n```\n2. 开启基于 web 的搜索页面\n```bash\n./imgfind serve 端口\n```\n\n## 编译问题\n\nwindows 需要设置环境变量 `RUSTFLAGS=-Ctarget-feature=+crt-static`\n\n```\n$env:RUSTFLAGS='-Ctarget-feature=+crt-static'\n```\n\nandroid 需要设置环境变量 `RUSTFLAGS=-C target-feature=+fp16`\n\n```bash\nexport RUSTFLAGS='-C target-feature=+fp16'\n```\n\n## 模型\n\n在 [这里](https://github.com/flaribbit/imgfind/releases/download/model/clip.zip) 下载模型，解压到 `clip` 目录中。\n\n```\n .\n├──  clip\n│   ├──  model.safetensors\n│   └──  tokenizer.json\n└──  imgfind.exe\n```\n\n# Local image search tool based on CLIP\n\n## Install\n\nFor windows users, it is recommend to use scoop\n\n```\nscoop install https://raw.githubusercontent.com/flaribbit/imgfind/master/scoop/imgfind.json\n```\n\nFor android users, you can download latest release in termux. For other platforms, you may clone this repo and compile it yourself.\n\n## Usage\n\n1. Create embeddings for images in `somepath` for search:\n```bash\n./imgfind add somepath\n```\n2. Start a web server on `port` for user interface:\n```bash\n./imgfind serve port\n```\n\n## Model\n\nDownload model from [here](https://github.com/flaribbit/imgfind/releases/download/model/clip.zip), then extract files into `clip` folder.\n\n```\n .\n├──  clip\n│   ├──  model.safetensors\n│   └──  tokenizer.json\n└──  imgfind.exe\n```\n\n## FAQ during build process\n\nOn windows you need to set env `RUSTFLAGS=-C target-feature=+crt-static`\n\n```\n$env:RUSTFLAGS='-C target-feature=+crt-static'\n```\n\nOn android you need to set env `RUSTFLAGS=-C target-feature=+fp16`\n\n```bash\nexport RUSTFLAGS='-C target-feature=+fp16'\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflaribbit%2Fimgfind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflaribbit%2Fimgfind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflaribbit%2Fimgfind/lists"}