windows 推荐使用 scoop 一键安装
scoop install https://raw.githubusercontent.com/flaribbit/imgfind/master/scoop/imgfind.json
android 可以使用 termux 下载最新 release 运行,其他系统目前只能自己编译。
- 为目录中的所有图片文件创建 embeddings,以便搜索:
./imgfind add 目录
- 开启基于 web 的搜索页面
./imgfind serve 端口
windows 需要设置环境变量 RUSTFLAGS=-Ctarget-feature=+crt-static
$env:RUSTFLAGS='-Ctarget-feature=+crt-static'
android 需要设置环境变量 RUSTFLAGS=-C target-feature=+fp16
export RUSTFLAGS='-C target-feature=+fp16'
在 这里 下载模型,解压到 clip
目录中。
.
├── clip
│ ├── model.safetensors
│ └── tokenizer.json
└── imgfind.exe
For windows users, it is recommend to use scoop
scoop install https://raw.githubusercontent.com/flaribbit/imgfind/master/scoop/imgfind.json
For android users, you can download latest release in termux. For other platforms, you may clone this repo and compile it yourself.
- Create embeddings for images in
somepath
for search:
./imgfind add somepath
- Start a web server on
port
for user interface:
./imgfind serve port
Download model from here, then extract files into clip
folder.
.
├── clip
│ ├── model.safetensors
│ └── tokenizer.json
└── imgfind.exe
On windows you need to set env RUSTFLAGS=-C target-feature=+crt-static
$env:RUSTFLAGS='-C target-feature=+crt-static'
On android you need to set env RUSTFLAGS=-C target-feature=+fp16
export RUSTFLAGS='-C target-feature=+fp16'