you are viewing a single comment's thread
view the rest of the comments
[–] 32 points 3 days ago (12 children)

aaargh this image sucks. It 100% looks like AI slop but at the same time I can't really find the definitive gotcha that reveals it as such. just smol inconsistencies you could explain away with human imperfections too, and the tingly spider sensation I get from the colors and the font.

  • source
  • parent
  • hideshow 12 child comments
  • [–] 60 points 3 days ago (3 children)

    It’s the pants. Specifically, the belt buckle and the artifacting in her pants.

    Sorry.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 14 points 3 days ago (3 children)

    The giveaway for me is the color grading. It's as if the entire image had a layer of brown or yellow layered over it- not as strong as the classic yellow one but it's definitely there.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 5 points 3 days ago (2 children)

    Can't you do that manually with an image editor?

  • source
  • parent
  • hideshow 2 child comments
  • [–] -2 points 2 days ago (1 child)

    Modern models don't really have tells anymore. They either explode really obviously or good enough that they just look like a normal casual artist.

    The small hints and tells just don't really happen anymore. Doubly so if words are added by hand :/

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 2 days ago

    You are absolutely wrong. Just go look at the recent AI flyer trend. AI has and will always have tells (as long as we talk about the traditional DCGAN distill noise to image concept that's the norm right now). You can minimize them with more effort, but a lot of people don't even go thru that effort or know that AI image gen extends far past the "ChatGPT make me a image" paradigm.

  • source
  • parent