Lastest News
Style2paints V2 is coming soon with better color!
Our new UI (Style2paints V1) is under construction now. You can try it directly!
PaintsTransfer: http://paintstransfer.com/
You have just found STYLE2PAINTS
📌GithubPage 📌GithubPageChinese 📌StyleTransfer
The previous version is now at 52.80.94.56:8000
The AI can paint on a sketch according to a given specific color style.
The AI can transfer illustrations' style.
Tuitions
Example 1 (Google Search results test)
A content sketch (the first google image search result of key word 'anime sketch') and some style images:
.
.
.
Results:
.
.
.
.
.
.
.
.
.
.
.
.
Example 2 (western sketch)
A western content sketch and 2 style images:
.
.
.
.
Example 3 (messy sketch)
A messy content sketch and 2 style images:
.
.
.
.
.
.
.
Example 4 (detailed sketch)
A detailed content sketch and 2 style images:
.
.
.
.
.
.
.
Example 5 (simple sketch)
A simple content sketch without shadow rendering and 2 style images:
.
.
.
.
.
.
.
CPU Server for Beginner
you need a python 3 environment.
pip install tensorflow
pip install keras
pip install chainer
pip install bottle
pip install gevent
pip install h5py
pip install opencv-python
git clone https://github.com/lllyasviel/style2paints.git
(then download all pretrained models from 'release' page and then put them in 'style2paints/server')
cd style2paints/server
python server.py cpu
GPU Server for Reseachers
you need a CUDA python 3.6 environment.
pip install tensorflow_gpu
pip install keras
pip install chainer
pip install cupy
pip install bottle
pip install gevent
pip install h5py
pip install opencv-python
git clone https://github.com/lllyasviel/style2paints.git
(then download all pretrained models from 'release' page and then put them in 'style2paints/server')
cd style2paints/server
python server.py
Model
Models are available in 'release' page.
- base_generator.net -> all rights reserved 2017 style2paints
- style2paints.net -> all rights reserved 2017 style2paints
- google_net.net -> from nico-opendata
Training Datasets
-
The recommended training dataset of illustrations is the 400k images from nico-opendata
-
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.