• Lewistrick@feddit.nl
    link
    fedilink
    English
    arrow-up
    3
    ·
    10 months ago

    Nice! Are you sure he’s in there exactly once? And is this completely the work of AI or is there human touch involved?

    • Last@lemmy.worldOP
      link
      fedilink
      English
      arrow-up
      8
      ·
      edit-2
      10 months ago

      Thanks! I didn’t have any input for the space station one, and honestly, it’s a bit of a mess; just a joke post, really. It looks cool on mobile, but you can’t see the people’s faces and figuring out the objects is tricky. I was kind of hoping others would jump in, try their own, or maybe offer some tips. Everything I post is just AI, nothing is edited by a human and I don’t use post processing after the AI generates it.

  • wagesj45@kbin.social
    link
    fedilink
    arrow-up
    3
    ·
    10 months ago

    I wonder if SD 1.5 would be better suited to this Where’s Waldo style, since generating scenes over 512x512 causes it to start repeating itself, with elements flowing from one 512 region to another. If someone with a ton of VRAM wants to test that theory for me, I’d appreciate it!