I’ve been trying to make a centaur since Chat GPT let me do AI images and I learned that you can use :: to make things merge, and it worked better. I got one that looked right, but if I tried to make sure it wore clothing it got even worse…

Attempts forcing clothing:

Attempts when I gave up on forcing clothing, it got it right once:

The one that worked:

  • tal@lemmy.today
    link
    fedilink
    English
    arrow-up
    4
    ·
    11 months ago

    Hmm. Stable Diffusion seems to want to separate the human and horse too.

    • BallShapedMan@lemmy.worldOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      11 months ago

      Weird right?

      I’ve been able to make every other fantasy creature I’ve tried but this one. Makes me wonder why?

      • tal@lemmy.today
        link
        fedilink
        English
        arrow-up
        6
        ·
        11 months ago

        If you figure that it’s been trained on very few centaurs and very many images of horses and of people – and of people riding horses – my guess is that it’ll try to make something that looks like what it’s been trained on.

      • wewbull@feddit.uk
        link
        fedilink
        English
        arrow-up
        2
        ·
        11 months ago

        Probably because 90+% of images it’s been trained on are people that don’t have horse bodies.

        Basically it’s over-trained on pictures of people.

          • BlueÆtherA
            link
            fedilink
            English
            arrow-up
            2
            ·
            edit-2
            11 months ago

            a faun

            SD (fullyREALXL_v30ForREAL) seems to want to draw one from A Midsummer’s Night Dream with full stage makeup on :/