Projecting into a GAN is searching for the representation of an image in that model. If you look hard enough you can find close matches for almost any image, even ones that don’t bear much resemblance to the model, but my favorite results are when you search just a little bit. This feels a lot more like asking the model, “What would Bill Hader look like as a cat?”
A banned game teenagers secretly play in Hogwarts.
StyleGAN neural network portraits cross trained on Magic the Gathering cards. This was so much cooler and more haunting than I imagined.
Just a quick post for now, as my original tweet was more popular than I expected and not everyone likes scrolling through tweet threads.