asanoviskhak / lama-cleaner

Image inpainting tool powered by SOTA AI Model

Lama Cleaner

A free and open-source inpainting tool powered by SOTA AI model.

example-0.24.0.mp4

Features

• Completely free and open-source, fully self-hosted, support CPU & GPU & M1/2
• Windows 1-Click Installer
• Native macOS app
• Multiple SOTA AI models
  • Erase model: LaMa/LDM/ZITS/MAT/FcF/Manga
  • Erase and Replace model: Stable Diffusion/Paint by Example
• Plugins for post-processing:
  • RemoveBG: Remove images background
  • RealESRGAN: Super Resolution
  • GFPGAN: Face Restoration
  • RestoreFormer: Face Restoration
  • Segment Anything: Accurate and fast interactive object segmentation
• FileManager: Browse your pictures conveniently and save them directly to the output directory.
• Docker Image
• More features at lama-cleaner-docs

Quick Start

Lama Cleaner make it easy to use SOTA AI model in just two commands:

# 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

Development

Only needed if you plan to modify the frontend and recompile yourself.

Frontend

Frontend code are modified from cleanup.pictures, You can experience their great online services here.

• Install dependencies:cd lama_cleaner/app/ && pnpm install
• Start development server: pnpm start
• Build: pnpm build