2024-01-21 16:25:50 +01:00
< h1 align = "center" > IOPaint< / h1 >
< p align = "center" > A free and open-source inpainting & outpainting tool powered by SOTA AI model.< / p >
2022-07-22 17:20:12 +02:00
< p align = "center" >
2024-01-21 16:25:50 +01:00
< a href = "https://github.com/Sanster/IOPaint" >
< img alt = "total download" src = "https://pepy.tech/badge/iopaint" / >
2022-07-22 17:20:12 +02:00
< / a >
2024-01-21 16:25:50 +01:00
< a href = "https://pypi.org/project/iopaint" >
< img alt = "version" src = "https://img.shields.io/pypi/v/iopaint" / >
2022-11-16 14:18:51 +01:00
< / a >
2022-12-11 15:50:37 +01:00
< a href = "" >
2024-01-21 16:25:50 +01:00
< img alt = "python version" src = "https://img.shields.io/pypi/pyversions/iopaint" / >
2022-10-08 06:55:51 +02:00
< / a >
2022-07-22 17:20:12 +02:00
< / p >
2024-01-24 15:21:47 +01:00
< p align = "center" >
< img alt = "python version" src = "https://github.com/Sanster/models/assets/3998421/561b8395-76a2-4c70-ab24-9f6986924c6a" height = 600 / >
< / p >
2021-12-12 07:54:37 +01:00
2022-07-22 17:20:12 +02:00
## Quick Start
2021-11-15 08:22:34 +01:00
2024-01-24 15:21:47 +01:00
### Start webui
2024-02-03 14:31:08 +01:00
IOPaint provides a convenient webui for using the latest AI models to edit your images.
2024-01-24 15:21:47 +01:00
You can install and start IOPaint easily by running following command:
2022-10-05 17:15:09 +02:00
2022-04-18 16:40:23 +02:00
```bash
2024-01-21 16:25:50 +01:00
# In order to use GPU, install cuda version of pytorch first.
# pip3 install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu118
2024-01-24 15:21:47 +01:00
# AMD GPU users, please utilize the following command, only works on linux, as pytorch is not yet supported on Windows with ROCm.
# pip3 install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/rocm5.6
2024-01-21 16:25:50 +01:00
pip3 install iopaint
iopaint start --model=lama --device=cpu --port=8080
2022-04-18 16:40:23 +02:00
```
2024-01-21 16:25:50 +01:00
That's it, you can start using IOPaint by visiting http://localhost:8080 in your web browser.
2022-11-21 07:02:44 +01:00
2024-01-24 15:21:47 +01:00
### Batch processing
2022-07-25 04:16:01 +02:00
2024-02-03 14:31:08 +01:00
You can also use IOPaint in the command line to batch process images:
2021-11-15 08:22:34 +01:00
2024-01-21 16:25:50 +01:00
```bash
iopaint run --model=lama --device=cpu \
--input=/path/to/image_folder \
--mask=/path/to/mask_folder \
--output=output_dir
```
2022-02-05 12:58:25 +01:00
2024-02-03 14:31:08 +01:00
`--input` is the folder containing input images, `--mask` is the folder containing corresponding mask images.
When `--mask` is a path to a mask file, all images will be processed using this mask.
2021-11-15 08:22:34 +01:00
2024-01-24 15:00:01 +01:00
You can see more information about the available models and plugins supported by IOPaint below.
2024-01-21 16:25:50 +01:00
## Features
2021-11-15 08:22:34 +01:00
2024-01-24 15:00:01 +01:00
- Completely free and open-source, fully self-hosted, support CPU & GPU & Apple Silicon
2024-01-21 16:25:50 +01:00
- Supports various AI models:
2024-01-24 15:21:47 +01:00
- Erase models: These models can be used to remove unwanted object, defect, watermarks, people from image.
2024-02-03 14:31:08 +01:00
- Stable Diffusion models: You can use any Stable Diffusion Inpainting(or normal) models from [Huggingface ](https://huggingface.co/models?other=stable-diffusion ) in IOPaint.
Some popular used models include: - [runwayml/stable-diffusion-inpainting ](https://huggingface.co/runwayml/stable-diffusion-inpainting ) - [diffusers/stable-diffusion-xl-1.0-inpainting-0.1 ](https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1 ) - [andregn/Realistic_Vision_V3.0-inpainting ](https://huggingface.co/andregn/Realistic_Vision_V3.0-inpainting ) - [Lykon/dreamshaper-8-inpainting ](https://huggingface.co/Lykon/dreamshaper-8-inpainting ) - [Sanster/anything-4.0-inpainting ](https://huggingface.co/Sanster/anything-4.0-inpainting ) - [Sanster/PowerPaint-V1-stable-diffusion-inpainting ](https://huggingface.co/Sanster/PowerPaint-V1-stable-diffusion-inpainting )
- Other Diffusion models:
2024-01-24 15:00:01 +01:00
- [Sanster/AnyText ](https://huggingface.co/Sanster/AnyText )
2024-01-21 16:25:50 +01:00
- [timbrooks/instruct-pix2pix ](https://huggingface.co/timbrooks/instruct-pix2pix )
2024-01-24 15:00:01 +01:00
- [Fantasy-Studio/Paint-by-Example ](https://huggingface.co/Fantasy-Studio/Paint-by-Example )
2024-02-03 14:31:08 +01:00
- [kandinsky-community/kandinsky-2-2-decoder-inpaint ](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint )
2024-01-24 15:21:47 +01:00
- Plugins
2024-01-21 16:25:50 +01:00
- [Segment Anything ](https://iopaint.com/plugins/interactive_seg ): Accurate and fast interactive object segmentation
- [RemoveBG ](https://iopaint.com/plugins/rembg ): Remove image background or generate masks for foreground objects
- [Anime Segmentation ](https://iopaint.com/plugins/anime_seg ): Similar to RemoveBG, the model is specifically trained for anime images.
- [RealESRGAN ](https://iopaint.com/plugins/RealESRGAN ): Super Resolution
- [GFPGAN ](https://iopaint.com/plugins/GFPGAN ): Face Restoration
- [RestoreFormer ](https://iopaint.com/plugins/RestoreFormer ): Face Restoration
- [FileManager ](https://iopaint.com/features/file_manager ): Browse your pictures conveniently and save them directly to the output directory.
- [Native macOS app ](https://opticlean.io/ ) for erase task