Neural style transfer consists in generating an image with the same "content" as a base image, but with the "style" of a different picture.
This is achieved through the optimization of a loss function that has 3 components: "style loss", "content loss", and "total variation loss".
This implementation uses TensorFlow2.x to train a fast style transfer network and Flask as an backend API.
Requirements:
- Flask
- Tensorflow 2.x
python3 app.py
Base Image
Style Image
Genrated Image