Upload a photo and see what you'd look like in an animated movie!
We've been working on Toonify HD, a much higher quality and resolution version of our neural network. It's currently an early prototype, but if you'd like to try it out head over to Toonify HD.
Yes we have an API you can use, check it out. This is just an early version and we plan to add more models and capabilities soon! Let us know if you have any feedback!
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.
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
We are now generously supported by DeepAI who are running the neural network backend for us. Although DeepAI are now doing most of the heavy lifting, there is still a bit of cost in running the site, and we're very grateful for those who have supported us on Ko-fi.
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.
We don't store any of the images uploaded or generated. We send the image to DeepAI's servers to run the network and then show you the results. No imagery is stored on our systems.
We use the open source dlib face detector to find faces, it's designed to pick up frontal faces but isn't perfect.
Not many characters from animated films wear glasses so the model seems to have learnt to mostly remove them.
Sometimes the site generates a lot of traffic and the DeepAI servers have trouble keeping up. You can either wait or become a supporter on Ko-fi to gain access to the version that runs on our hardware.
This website was created by Justin Pinkney and Doron Adler. It uses deep learning to toonify images of faces. If you want to learn more about how this was trained, built, and deployed, the best place to look is my blog: www.justinpinkney.com