cross-posted from: https://programming.dev/post/3974080
Hey everyone. I made a casual survey to see if people can tell the difference between human-made and AI generated art. Any responses would be appreciated, I’m curious to see how accurately people can tell the difference (especially those familiar with AI image generation)
This paper is just about stock photos or video game art with enough dupes or variations that they didn’t get cut from the training set. The repeated images were included frequently enough to overfit. Which is something we already knew. That doesn’t really go to proving if diffusion models learn like humans or not. Not that I think they do.
Sure, it’s not proof, but it gives a good starting point. Non-overfitted images would still have this effect (to a lesser extent), and this would never happen to a human. And it’s not like the prompts were the image labels, the model just decided to use the stock image as a template (obvious in the case with the painting).