DeepNeuralAI/CV-Neural-Style-Transfer

Use neural representations to separate and recombine content and style of images, for the creation of artistic images

CV-Neural-Style-Transfer

Implementation of A Neural Algorithm of Artistic Style By Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

Demo

How to use Streamlit App

1. Choose a content image
2. Choose a style image
3. On left sidebar, click `Generate`
4. Adjust hyperparameters if needed (default learning_rate = 0.02)

How to run this demo

The demo requires Python 3.6 or later (TensorFlow is not yet compatible with later versions). We suggest creating a new virtual Python 3.6+ environment, then running:

git clone https://github.com/DeepNeuralAI/CV-Neural-Style-Transfer.git
cd CV-Neural-Style-Transfer
pip install -r requirements.txt
streamlit run app.py

Gallery

Content & Style	Generated

Credit

Modified code from Style Transfer

Inspired from A Neural Algorithm of Artistic Style