I can tell even “good” AI images because of the weird over manufactured look, kinda hard to describe it’s kinda like how fake leather feels wrong. But anyways this has the same weird energy as those weirdly gay Sino-Soviet propaganda posters.
It’s like, the more you look at it, the worse it looks, even though it looks good at first glance. Typically, when a human draws something that gets worse the more you look at it, then it already looks bad at first glance. I
I can tell even “good” AI images because of the weird over manufactured look, kinda hard to describe it’s kinda like how fake leather feels wrong. But anyways this has the same weird energy as those weirdly gay Sino-Soviet propaganda posters.
Why is it always so beige?
Bias in the Trainingdata
I like to call it “ChatGPT sepia”
The sepia from old comic books and newspaper comic strips
Guy on the right has a “uni-finger” haha.
His name is Chad
It’s like, the more you look at it, the worse it looks, even though it looks good at first glance. Typically, when a human draws something that gets worse the more you look at it, then it already looks bad at first glance. I
There’s that weird colour dithering AI always does. It’s not a consistent colour, it’s grainy like it uses video stativ/noise.
It literally does, every AI image starts as gaussian noise.
There’s a kind of ChatGPT sepia that it loves to use, then it’s version of “comic book panel” is apparently 1950’s public domain themed.