AI-based generative art tools are becoming increasingly accessible. I’m using a tool that links two neural networks: CLIP and VQ-GAN, to ingest text and generate images, and the results are amazing to say the least. The details are well-documented, so I’ll let others explain what’s going on in more depth. A tutorial on how to get started can be found here.
I rendered NBA Jam 70 different ways, keeping the subject matter the same and varying the style with every iteration. When I say “style” I mean anything that came to mind that might modify it in an interesting way.
Every one of these renderings was done with input: “NBA Jam | [style]” using 400 iterations (I’ve found that you get a pretty good sense of where it’s going by that point.)
Why pick NBA Jam? It seemed to produce interesting results.