What is this?
This is an implementation of the Fast Neural Style Transfer algorithm running purely on the browser using the Deeplearn.JS library. Basically, a neural network attempts to "draw" one picture, the Content, in the style of another, the Style.
Is my data safe? Can you see my webcam pics?
Your data and pictures here never leave your computer! In fact, this is one of the main advantages of running neural networks in your browser. Instead of sending us your data, we send *you* both the model *and* the code to run the model. These are then run by your browser.
.How big are the models I'm downloading?
For each available style, your browser will download a model around ~6.6MB in size. Be careful if you have limited bandwidth (mobile data users).
Is the code open source?
Yup! Visit https://github.com/reiinakano/fast-style-transfer-deeplearnjs to examine the code. Also, feel free to submit any issues or pull requests to the repository as well.
This web page is ugly.
I know. Sorry, I'm not really a UI designer. I have about a 10 minute tolerance for tweaking HTML and CSS until I give up. The good news is, it's all open source on Github! If you want to help improve the page's design, please send a pull request! :)
Credits
This demo was put together by Reiichiro Nakano but could never have been done without the following:
- The authors of the original Neural Style Transfer paper.
- The authors of the paper introducing Real-Time Style Transfer.
- The author of the fast-style-transfer Github repository.
- The authors of Deeplearn.JS