About

Fast Style Transfer recomposes images in the style of other images.

This is a demo of Fast Style Transfer in ml5.

You can choose different images, upload your own image, or turn on your webcam as an input, and choose a style in the middle, the output image will appear on the right.

Check it out here: https://yining1023.github.io/fast_style_transfer_in_ML5

The code is here: https://github.com/yining1023/fast_style_transfer_in_ML5

Credits: The code and models are based on deeplearn.js demo by reiinakano.

Here is some slides that introduce what is style transfer and how does it work from my Machine Learning for the Web class - week 3.

To train your own style transfer, here is some instructions for training a style transfer model with Spell: https://github.com/yining1023/styleTransfer_spell. You can also watch the videos below.

In this video, Yining Shi demonstrates how to train a "Style Transfer Model" using Spell (Sign up here: https://spell.run/codingtrain). In Part 2, Yining will use this trained model to style a real-time image, in browser, using ml5.js and p5.js. #ThisDotStyle #StyleTransfer #MachineLearning 🎥 Part 2: https://youtu.be/S_I0SGAO73A This video is sponsored by Spell.

In this video, Yining Shi uses this trained model to style a real-time image, in browser, using ml5.js and p5.js. #ThisDotStyle #StyleTransfer #MachineLearning To sign up to Spell: https://spell.run/codingtrain 🎥 Part 1: https://youtu.be/STHRNIJc-vI This video is sponsored by Spell.