this post was submitted on 05 Sep 2025
560 points (90.7% liked)
People Twitter
10395 readers
1595 users here now
People tweeting stuff. We allow tweets from anyone.
RULES:
- Mark NSFW content.
- No doxxing people.
- Must be a pic of the tweet or similar. No direct links to the tweet.
- No international politcs
- Be excellent to each other.
- Provide an archived link to the tweet (or similar) being shown if it's a major celebrity, figure or any politician. https://web.archive.org/save is an option. Archive.is is no longer recommended because they remove/alter content.
- If a tweet (or similar) makes a statement of fact, either mark it as "satire" in the body or provide the original source link backing up the statement
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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
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.
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