I love to draw butts. I just can’t help it. It may seem juvenile, but it always brings a smile to my face in an almost therapeutic way. (And it all started years ago.) So what better way to harness the unparalleled power of machine learning than to force an artificial intelligence to also draw pictures of butts.
To generate the images, I first needed to create some training material. I set up a grid and drew 440 butts in a grid format over 22 pages. I scanned each page, loaded them as a stack into Photoshop, and then sliced up the image based on the original grid. It was then easy to export each individual drawing as a square image that could be used to train the model.
I took my source material and trained a new model with RunwayML. I opted to use StyleGAN 1 and started with the base model of nebulas, and iterated it over 6,000 steps.
It was interesting to see that it evolved from star stuff to butt stuff pretty quickly and early on, and then spent a majority of the time fine tuning details.
The results were surprisingly good. I ended up getting some noise from the paper texture in the scans, which is very obvious in the latent space walk pictured here. But outside of that, I feel like most of the generated images are indeterminate from ones drawn by yours truly.
Try it for yourself!
This was originally posted on Artificial Imagery, my other site for AI-generated images.