Skip to content

weipanshao/style2paints

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

200 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Welcome to STYLE2PAINTS 2.0 !

First of all, why not spend 5 minutes to try it yourself!

WebAPP: PaintsTransfer

The AI can paint on a sketch according to a given specific color style.

The AI can transfer illustrations' style.

News: We will release STYLE2PAINTS 2.1 soon.

Tutorial

Tutorial001(BiliBili)

Screenshots

web_preview

web_preview

web_preview

web_preview

web_preview

web_preview

web_preview

web_preview

web_preview

web_preview

Launch Server

you need a python 3.5/3.6 environment.

pip install tensorflow_gpu
pip install keras
pip install bottle
pip install gevent
pip install h5py
pip install opencv-python
pip install scikit-image
git clone https://github.com/lllyasviel/style2paints.git
(then download all pretrained models from 'release' page and then decompress them to 'style2paints/server')
cd style2paints/server
python server.py

Models

Models are available in releases page.

Currently, we reserve all rights about all these models. The only thing you can do with these models is to play with it on your PC.

ALL COMMERCIAL USE IS PROHIBITED!

ALL RESEARCH USE IS ALSO PROHIBITED!

(If you are writing a paper and need a comparison, you can use the online demo to get results, in absense of these pretrained models.)

Training Datasets

  1. The recommended training dataset of illustrations is the 400k images from nico-opendata

  2. The recommended training sketches is from sketchKeras

Community

QQ Group ID: 184467946

Acknowledgements

Thanks a lot to TaiZan. This project could not be achieved without his great help.

About

sketch + style = paints 🎨

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages

  • JavaScript 66.4%
  • Python 20.6%
  • CSS 8.8%
  • HTML 4.2%