This project utilizes neural style transfer techniques to transfer the style of a given content image into another image provided by the style given. The paper titled A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, (2015) has served as a fundamental reference for this project.
Website: https://melo04.github.io/neural-style-transfer/
Neural Style Transfer (NST) is an optimization technique used to merge two images—a content image and a style reference image and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image. Below contains an example that maps the artistic style of The Starry Night onto a night-time photograph of the The Hoover Tower Observation Platform nearby Stanford University:
Applying the style of different images produce different interesting results. Here we renders a photograph to a variety of styles. Feel free to try it out in the website too.
The following reproduce Figure 3 from the paper, which renders a photograph of the Neckarfront in Tübingen, Germany in the style of 4 different iconic paintings The Starry Night, Composition VII, The Scream, Corridor:
The relative weight of the style and content can be controlled.
Example below renders a lion photograph image with an increasing image style size applied to the style of Amadeo Cardoso
- To run it locally, install Yarn and run the command below in your terminal to get all the dependecies.
yarn run prep- Then, run this command below and go to
localhost:9966to view the web application.
yarn run start