Toonify Yourself

Sorry Toonify Yourself is (mostly) offline for the moment!

It was a popular idea and server costs were going up quickly so we decided to turn it off. Thanks for everyone who tried out the model and shared the results.

We're currently working on bringing it back for everyone to try for free and expect it will be soon! Keep an eye on my blog or Twitter feed to stay up to date!

In the mean time, if you're really keen to get access to the site, please make a small donation to the running costs through the ko-fi link below. After you've made the donation you'll get a special secret link to use the web app as much as you like until we can bring it back for free.

Frequently Asked Questions

How does this work?

This toonification system is made using deep learning. It's based on distillation of a blended StyleGAN models into a pix2pixHD image to image translation network.

For information on all the technical details of how this works, see my blog post Making Toonify.

Why did you take it down? Will it be back?

This has just been a fun side project for us, and the cloud bills were growing pretty quickly, so we decided to pull the plug. If you're interested in the details of how we deployed the site, how many images we served, and the costs involved, see my blog.

We're currently working to bring back the website in a free and sustainable way for everyone, we fully expect this should happen pretty soon!

How did you come up with this idea?

This all started from some earlier experiments Doron shared on Twitter that got a lot of interest. For a description of those early experiments see this blog post on self toonification, the idea is the same, but the method is different (and not really suitable for hosting as a webapp).

Going even futher back in time, this was all based on some new methods of mixing StyleGAN models I came up with trying to make realistic Ukiyo-e portraits

How do I get good results?

The algorithm works best with high resolution images without much noise. Looking straight on to the camera also seem to work best. Something like a corporate headshot tends to work well.

Do you store my photo?

We don't store any of the images uploaded or generated. Once the toonification has finished running no images are kept on our systems.

My face wasn't found!

We use the open source dlib face detector to find faces, it's designed to pick up frontal faces but isn't perfect.

Where did my glasses go?

Not many characters from animated films wear glasses so the model seems to have learnt to mostly remove them.

Toonify Yourself!

Examples