• 4am@lemmy.zip
    link
    fedilink
    arrow-up
    2
    ·
    2 days ago

    Wait, does that mean the whole image is generated or that the AI wrote the captions?

    • lime!@feddit.nu
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 day ago

      text was added manually. if it was all one pass there would be space for the text in the image. image models are sticklers for consistency.