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

  • effward@lemmy.worldOP
    link
    fedilink
    English
    arrow-up
    2
    ·
    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
      link
      fedilink
      arrow-up
      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.