Cartoony fonts, way too much text everywhere, no visual higherarchy, colored rounded boxes, why does it all have seemingly one style rather than having multiple like you see in other ai mediums?

I hate generative ai btw I was just wondering

  • cecilkorik@piefed.ca
    link
    fedilink
    English
    arrow-up
    3
    ·
    2 days ago

    it’s a language model. You can give it any kind of prompt you want. How effectively it interprets those instructions is a separate discussion, but in general newer models expand on those sort of capabilities, they don’t strip them out.

    • Starya67@lemmy.world
      link
      fedilink
      arrow-up
      3
      ·
      2 days ago

      Aight. I just tried again for science. I gave it very detailed instructions and it produced a person with three arms. I did not specify three arms.

        • jacksilver@lemmy.world
          link
          fedilink
          arrow-up
          6
          ·
          2 days ago

          I like how this sounds kinda like a bratty response, but is legitamte advice.

          If you’re not aware, there is the concept of “negative prompts” with image generation where you basically tell it not to draw something ugly or wrong, but also can try to supress certain things too like three arms.