• 0ops@lemm.ee
    link
    fedilink
    arrow-up
    6
    ·
    4 months ago

    There’s no way it’d get all of the text on the shirts and signs right

    • Gabu@lemmy.ml
      link
      fedilink
      arrow-up
      2
      arrow-down
      1
      ·
      4 months ago

      I don’t expect everyone to know the different features of a “stable diffusion” style AI, but you can easily do something called img2img or inpainting, where you use transformations on a base image to help generate something more realistic. The current state of the art can easily generate readable text.