kamp/IOPaint

Fork 0

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

inpainting lama latent-diffusion mat pytorch stable-diffusion zits

Go to file

Qing 71351f68a7 fix setup.py on windows		2024-01-24 21:54:54 +08:00
.github	Update issue templates	2023-02-17 10:01:20 +08:00
assets	Add files via upload	2023-05-18 22:25:41 +08:00
docker	update dockerfile	2023-05-19 21:46:49 +08:00
iopaint	beta9	2024-01-21 23:33:32 +08:00
scripts	get samplers from backend	2024-01-02 14:34:36 +08:00
web_app	add AnyText	2024-01-21 23:25:50 +08:00
.gitignore	update gitignore	2024-01-05 15:21:25 +08:00
build_docker.sh	update dockerfile	2023-01-20 09:50:14 +08:00
LICENSE	init	2021-11-15 22:21:01 +08:00
main.py	rename to iopaint	2024-01-05 15:19:23 +08:00
publish.sh	update publish	2024-01-05 16:27:33 +08:00
README.md	add AnyText	2024-01-21 23:25:50 +08:00
requirements-dev.txt	update	2023-12-22 14:00:30 +08:00
requirements.txt	beta10	2024-01-21 23:43:25 +08:00
setup.py	fix setup.py on windows	2024-01-24 21:54:54 +08:00

README.md

IOPaint

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

python version

Quick Start

IOPaint provides an easy-to-use webui for utilizing the latest AI models. The installation process for IOPaint is also simple, requiring just two commands:

# 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
pip3 install iopaint
iopaint start --model=lama --device=cpu --port=8080

That's it, you can start using IOPaint by visiting http://localhost:8080 in your web browser.

You can also use IOPaint in the command line to batch process images:

iopaint run --model=lama --device=cpu \
--input=/path/to/image_folder \
--mask=/path/to/mask_folder \
--output=output_dir

--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.

You can see more information about the models and plugins supported by IOPaint below.

Features

Completely free and open-source, fully self-hosted, support CPU & GPU & M1/2
Supports various AI models:
- Inpainting models: These models are usually used to remove people or objects from images.
- Stable Diffusion models: These models have stronger generation abilities, allowing them to generate new objects on images, or to expand existing images. You can use any Stable Diffusion Inpainting(or normal) models from Huggingface in IOPaint. Some commonly used models are listed below:
- Other Diffusion models:
  - Sanster/AnyText: Generate text on images
  - timbrooks/instruct-pix2pix
  - Fantasy-Studio/Paint-by-Example: Generate images from text
  - kandinsky-community/kandinsky-2-2-decoder-inpaint
Plugins for post-processing:
- Segment Anything: Accurate and fast interactive object segmentation
- RemoveBG: Remove image background or generate masks for foreground objects
- Anime Segmentation: Similar to RemoveBG, the model is specifically trained for anime images.
- RealESRGAN: Super Resolution
- GFPGAN: Face Restoration
- RestoreFormer: Face Restoration
FileManager: Browse your pictures conveniently and save them directly to the output directory.
Native macOS app for erase task
More features at IOPaint Docs