• @iopq
    link
    03 hours ago

    Creating abstract art by moving pixels around is not anywhere close to what we mean by image generation. At no point did this other software generate something from a prompt

    • @[email protected]
      link
      fedilink
      12 hours ago

      in any way shape or form

      I’d normally accept the challenge if you didn’t add that. You did though and it, namely a system (arguably intelligent) made an image, several images in fact. The fact that we dislike or like the aesthetics of it or that the way it was done (without prompt) is different than how it currently is remains irrelevant according to your own criteria, which is none. Anyway my point with AARON isn’t about this piece of work specifically, rather that there is prior work, and this one is JUST an example. Consequently the starting point is wrong.

      Anyway… even if you did question this, I argued for more, showing that I did try numerous (more than 50) models, including very current ones. It even makes me curious if you, who is arguing for the capabilities and their progress, if you tried more models than I did and if so where can I read about it and what you learned about such attempts.