<p align="center">
<img alt="logo" height=256 src="./assets/logo.png" />
</p>
<h1 align="center">Lama Cleaner</h1>
<p align="center">A free and open-source inpainting tool powered by SOTA AI model.</p>
<p align="center">
<a href="https://github.com/Sanster/lama-cleaner">
<img alt="total download" src="https://pepy.tech/badge/lama-cleaner" />
</a>
<a href="https://pypi.org/project/lama-cleaner/">
<img alt="version" src="https://img.shields.io/pypi/v/lama-cleaner" />
</a>
<a href="https://colab.research.google.com/drive/1e3ZkAJxvkK3uzaTGu91N9TvI_Mahs0Wb?usp=sharing">
<img alt="Open in Colab" src="https://colab.research.google.com/assets/colab-badge.svg" />
</a>
<a href="https://huggingface.co/spaces/Sanster/Lama-Cleaner-lama">
<img alt="Hugging Face Spaces" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue" />
</a>
<a href="">
<img alt="python version" src="https://img.shields.io/pypi/pyversions/lama-cleaner" />
</a>
<a href="https://hub.docker.com/r/cwq1913/lama-cleaner">
<img alt="version" src="https://img.shields.io/docker/pulls/cwq1913/lama-cleaner" />
</a>
</p>
https://user-images.githubusercontent.com/3998421/196976498-ba1ad3ab-fa18-4c55-965f-5c6683141375.mp4
## 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)
- [Native macOS app](https://opticlean.io/)
- 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
- [FileManager](https://lama-cleaner-docs.vercel.app/features/file_manager): Browse your pictures conveniently and save them directly to the output directory.
- 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`
Raw data
{
"_id": null,
"home_page": "https://github.com/Sanster/lama-cleaner",
"name": "lama-cleaner",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "PanicByte",
"author_email": "cwq1913@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/8b/2d/8deb953d4dd20f513c018fbfa9f4ed23f8512da1e03db217b9f0f9c3e556/lama-cleaner-1.2.4.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img alt=\"logo\" height=256 src=\"./assets/logo.png\" />\n</p>\n<h1 align=\"center\">Lama Cleaner</h1>\n<p align=\"center\">A free and open-source inpainting tool powered by SOTA AI model.</p>\n\n<p align=\"center\">\n <a href=\"https://github.com/Sanster/lama-cleaner\">\n <img alt=\"total download\" src=\"https://pepy.tech/badge/lama-cleaner\" />\n </a>\n <a href=\"https://pypi.org/project/lama-cleaner/\">\n <img alt=\"version\" src=\"https://img.shields.io/pypi/v/lama-cleaner\" />\n </a>\n <a href=\"https://colab.research.google.com/drive/1e3ZkAJxvkK3uzaTGu91N9TvI_Mahs0Wb?usp=sharing\">\n <img alt=\"Open in Colab\" src=\"https://colab.research.google.com/assets/colab-badge.svg\" />\n </a>\n\n <a href=\"https://huggingface.co/spaces/Sanster/Lama-Cleaner-lama\">\n <img alt=\"Hugging Face Spaces\" src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue\" />\n </a>\n\n <a href=\"\">\n <img alt=\"python version\" src=\"https://img.shields.io/pypi/pyversions/lama-cleaner\" />\n </a>\n <a href=\"https://hub.docker.com/r/cwq1913/lama-cleaner\">\n <img alt=\"version\" src=\"https://img.shields.io/docker/pulls/cwq1913/lama-cleaner\" />\n </a>\n</p>\n\nhttps://user-images.githubusercontent.com/3998421/196976498-ba1ad3ab-fa18-4c55-965f-5c6683141375.mp4\n\n## Features\n\n- Completely free and open-source, fully self-hosted, support CPU & GPU & M1/2\n- [Windows 1-Click Installer](https://lama-cleaner-docs.vercel.app/install/windows_1click_installer)\n- [Native macOS app](https://opticlean.io/)\n- Multiple SOTA AI [models](https://lama-cleaner-docs.vercel.app/models)\n - Erase model: LaMa/LDM/ZITS/MAT/FcF/Manga\n - Erase and Replace model: Stable Diffusion/Paint by Example\n- [Plugins](https://lama-cleaner-docs.vercel.app/plugins) for post-processing:\n - [RemoveBG](https://github.com/danielgatis/rembg): Remove images background \n - [RealESRGAN](https://github.com/xinntao/Real-ESRGAN): Super Resolution\n - [GFPGAN](https://github.com/TencentARC/GFPGAN): Face Restoration\n - [RestoreFormer](https://github.com/wzhouxiff/RestoreFormer): Face Restoration\n - [Segment Anything](https://lama-cleaner-docs.vercel.app/plugins#interactive-segmentation): Accurate and fast interactive object segmentation\n- [FileManager](https://lama-cleaner-docs.vercel.app/features/file_manager): Browse your pictures conveniently and save them directly to the output directory.\n- More features at [lama-cleaner-docs](https://lama-cleaner-docs.vercel.app/)\n\n## Quick Start\n\nLama Cleaner make it easy to use SOTA AI model in just two commands:\n\n```bash\n# In order to use the GPU, install cuda version of pytorch first.\n# pip install torch==1.13.1+cu117 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu117\npip install lama-cleaner\nlama-cleaner --model=lama --device=cpu --port=8080\n```\n\nThat's it, Lama Cleaner is now running at http://localhost:8080\n\nSee all command line arguments at [lama-cleaner-docs](https://lama-cleaner-docs.vercel.app/install/pip)\n\n## Development\n\nOnly needed if you plan to modify the frontend and recompile yourself.\n\n### Frontend\n\nFrontend code are modified from [cleanup.pictures](https://github.com/initml/cleanup.pictures), You can experience their\ngreat online services [here](https://cleanup.pictures/).\n\n- Install dependencies:`cd lama_cleaner/app/ && pnpm install`\n- Start development server: `pnpm start`\n- Build: `pnpm build`\n",
"bugtrack_url": null,
"license": "",
"summary": "Image inpainting tool powered by SOTA AI Model",
"version": "1.2.4",
"project_urls": {
"Homepage": "https://github.com/Sanster/lama-cleaner"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "49ccfe1e91c15225925538b4952effeca7ceed3cac4c4fc69c6a536aebcf7f91",
"md5": "6cba66dd7cd50bea79301de114f2935c",
"sha256": "7457feefc8e7e1c316eafeb239256c6b70babb20aa56d7acbc5cea648de8aad2"
},
"downloads": -1,
"filename": "lama_cleaner-1.2.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6cba66dd7cd50bea79301de114f2935c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 6760035,
"upload_time": "2023-10-05T13:56:43",
"upload_time_iso_8601": "2023-10-05T13:56:43.719470Z",
"url": "https://files.pythonhosted.org/packages/49/cc/fe1e91c15225925538b4952effeca7ceed3cac4c4fc69c6a536aebcf7f91/lama_cleaner-1.2.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8b2d8deb953d4dd20f513c018fbfa9f4ed23f8512da1e03db217b9f0f9c3e556",
"md5": "0c45adb70cc2b2675dce17213abc8bfa",
"sha256": "104797879f240b5d99a7f460cdb0965be392f9300505d5574eb521458782d95f"
},
"downloads": -1,
"filename": "lama-cleaner-1.2.4.tar.gz",
"has_sig": false,
"md5_digest": "0c45adb70cc2b2675dce17213abc8bfa",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 5910838,
"upload_time": "2023-10-05T13:56:48",
"upload_time_iso_8601": "2023-10-05T13:56:48.421524Z",
"url": "https://files.pythonhosted.org/packages/8b/2d/8deb953d4dd20f513c018fbfa9f4ed23f8512da1e03db217b9f0f9c3e556/lama-cleaner-1.2.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-05 13:56:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Sanster",
"github_project": "lama-cleaner",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "torch",
"specs": [
[
">=",
"1.9.0"
]
]
},
{
"name": "opencv-python",
"specs": []
},
{
"name": "flask",
"specs": [
[
"==",
"2.2.3"
]
]
},
{
"name": "flask-socketio",
"specs": []
},
{
"name": "simple-websocket",
"specs": []
},
{
"name": "flask_cors",
"specs": []
},
{
"name": "flaskwebgui",
"specs": [
[
"==",
"0.3.5"
]
]
},
{
"name": "pydantic",
"specs": []
},
{
"name": "rich",
"specs": []
},
{
"name": "loguru",
"specs": []
},
{
"name": "yacs",
"specs": []
},
{
"name": "diffusers",
"specs": [
[
"==",
"0.16.1"
]
]
},
{
"name": "transformers",
"specs": [
[
"==",
"4.27.4"
]
]
},
{
"name": "gradio",
"specs": []
},
{
"name": "piexif",
"specs": [
[
"==",
"1.1.3"
]
]
},
{
"name": "safetensors",
"specs": []
},
{
"name": "omegaconf",
"specs": []
},
{
"name": "controlnet-aux",
"specs": [
[
"==",
"0.0.3"
]
]
},
{
"name": "werkzeug",
"specs": [
[
"==",
"2.2.2"
]
]
}
],
"lcname": "lama-cleaner"
}