[burlesona]

It's interesting to me, the model does not know what a house is like, it knows what pictures of houses are like. So it does a good job of making pictures that look like pictures of houses. But if you look closely, a lot of the details are really weird, unbuildable, or just non-sensical.

All of the image-gen models have this problem - look at the hands and faces in the generated images of people and there are often bizarre deformations.

It's fascinating because it's the opposite of how children learn to draw. They tend to think about the pieces that make a thing and then try to put all the pieces on paper, and they end up making a drawing that (for instance) looks nothing like a person but has two eyes, a nose, a mouth, etc. in roughly the right relation to each other. (They rarely draw ears though!) The child is thinking about "what makes a face a face" and then trying to represent it. The ML model is sort of distributing pixels in a probabilistic way that comes up with something very similar to the pixels in a sample image in its training set, superficially much better than a kids drawing and yet in some ways much worse upon close inspection.

[smegsicle]

perspective and shadows in this one are particularly avant garde

https://thishousedoesnotexist.org/4036194

[kazinator]

> a lot of the details are really weird, unbuildable, or just non-sensical.

You would see a lot more of these on the images that didn't make the gallery.