> The image generator seems to understand that you can’t see through opaque objects
I thought this isn't the case for Stable Diffusion. Wasn't it the humans making the source images who understood things like that, and their knowledge became encoded in the latent space of the model? I'm not an expert. Please correct me here.
I just tried it out. This prompt (without any additional description) didn't had a satisfying expected output with Stable Diffusion 1.5.
With some other keywords, it generated some cool looking images but not any where there was a clear transparent horse and visible legs of an astronaut or something.
It is generally just very hard to compose a prompt where multiple subjects interact in a specific instructed way.
I thought this isn't the case for Stable Diffusion. Wasn't it the humans making the source images who understood things like that, and their knowledge became encoded in the latent space of the model? I'm not an expert. Please correct me here.