I have the same reaction. They're like an alien with only a description of human activities but no real knowledge of behavior or society, tried to create a painting. Everything is strangely squished, there's no clear dividing line between one thing and another, nothing is a functional symbol but just an impression of a symbol. "Humans like yellow; lets put a yellow shape in there!"

This technology has been developing very fast; pictures look a lot more realistic than they used to, and you can guide the process with real images along the way. (Zoetrope is a good notebook for this.)

The main issue is that it's hard to generate good looking faces without a specialized model (because we're so picky about humans), and the companies generating models like DALL-E don't want to teach them how to generate faces in case of bias.

GAN art is really a one trick pony.

I loved it at first and got quite into it but I have seen enough of these images now that the novelty has worn off and they are just kind of shit.

Physical painting inspired by GAN art might be cool but I don't have the talent for that. There is also something lost for sure when I know I could make a 100 of these album covers in maybe 20 minutes of tinkering around?

They should put a human in a fMRI scanner, and place this in the feedback loop of the GAN. When the human feels repulsion, the fMRI scanner picks this up and sends negative feedback to the network.

The human would most likely quickly be desensitized and only output feelings of self hatred and suicide. But to be sure we should start a multibillion dollar startup that generates jobs for millions of starving third worlders.