Tried multiple prompts to generate an image of a woman cutting her own hair using portals and this is the best I got 🙁

  • jet@hackertalks.comEnglish
    63·
    1 year ago

    It’s an interdimensional portal, she’s cutting her hair in a different reality, once she’s done they’ll switch

  • KazuyaDarklight@lemmy.worldEnglish
    9·
    1 year ago

    Portals TM kind of represents a specific interpretation of how a set of portals would be used. If you didn’t, I’d try emphasizing that it’s identical twins wearing the same clothes.

  • IamLost@lemmy.world
    72·
    1 year ago

    This is why I think AI is a good thing for artists because this is a good start. It wouldn’t take much for an artist to alter it now to get what you want. Saved a lot of time which is the point people lose sight of.

    • effward@lemmy.worldOPEnglish
      1·
      1 year ago

      I used DALL-E 3 via chat GPT interface, so chat GPT manipulates the prompt before passing it to DALL-E, but I put this into chat GPT:

      A woman using a portal gun as a mirror so that she can see her back so that she can cut her own hair

      Trying more specific descriptions about having orange portal behind her and having hands reaching out of the portal led to worse results…

      • Adalast@lemmy.world
        2·
        1 year ago

        Maybe try adding the Portal 2 name into the prompt. I don’t use DALL-E as the FOSS solutions just give me so much control, but I suspect that the names Portal/Portal 2 and Aperture Science are in the corpus for DALL-E. I will have to test my SDXL setup to see what it comes out with. Are you able to use Controlnets with DALL-E? If so, it might be worth doing a basic sketch and having it fill in details.

  • KingBoo@lemmy.world
    31·
    1 year ago

    Could You establish how you expect portals to work before the prompt about the art?