## Features
- Completely free and open-source, fully self-hosted, support CPU & GPU & M1/2
- [Windows 1-Click Installer](https://lama-cleaner-docs.vercel.app/install/windows_1click_installer)
- Multiple SOTA AI [models](https://lama-cleaner-docs.vercel.app/models)
- Erase model: LaMa/LDM/ZITS/MAT/FcF/Manga
- Erase and Replace model: Stable Diffusion/Paint by Example
- [Plugins](https://lama-cleaner-docs.vercel.app/plugins) for post-processing:
- [RemoveBG](https://github.com/danielgatis/rembg): Remove images background
- [RealESRGAN](https://github.com/xinntao/Real-ESRGAN): Super Resolution
- [GFPGAN](https://github.com/TencentARC/GFPGAN): Face Restoration
- [RestoreFormer](https://github.com/wzhouxiff/RestoreFormer): Face Restoration
- [Segment Anything](https://lama-cleaner-docs.vercel.app/plugins#interactive-segmentation): Accurate and fast interactive object segmentation
- More features at [lama-cleaner-docs](https://lama-cleaner-docs.vercel.app/)
## Quick Start
Lama Cleaner make it easy to use SOTA AI model in just two commands:
```bash
# In order to use the GPU, install cuda version of pytorch first.
# pip install torch==1.13.1+cu117 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu117
pip install lama-cleaner
lama-cleaner --model=lama --device=cpu --port=8080
```
That's it, Lama Cleaner is now running at http://localhost:8080
See all command line arguments at [lama-cleaner-docs](https://lama-cleaner-docs.vercel.app/install/pip)
## Development
Only needed if you plan to modify the frontend and recompile yourself.
### Frontend
Frontend code are modified from [cleanup.pictures](https://github.com/initml/cleanup.pictures), You can experience their
great online services [here](https://cleanup.pictures/).
- Install dependencies:`cd lama_cleaner/app/ && pnpm install`
- Start development server: `pnpm start`
- Build: `pnpm build`
