This website that threatens anyone who right clicks - eviltoast
  • gregorum@lemm.ee
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    1
    ·
    8 months ago

    Lol… I hope you didn’t sprain something with all those mental gymnastics. In the meantime, perhaps you should educate yourself a bit more on AI, LLV’s, and, perhaps, just a little bit on art.

      • gregorum@lemm.ee
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        2
        ·
        edit-2
        8 months ago

        OK, if you think what you just said made sense, then you either didn’t read the link you just posted or you clearly didn’t understand it. And you certainly have no clue what you’re talking about.

        But you’re certainly helping to make my point for me

        • A_Very_Big_Fan@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          arrow-down
          4
          ·
          edit-2
          8 months ago

          AI, unlike a human, cannot create unique works of art. it can old produce an algorithmically-derived malange of its source-data recomposited in novel forms

          Find me a single sentence in that entire article that suggests AI art is composites of source data

          You can’t, because how it actually works is wildly different than how you want to believe it works.

          • gregorum@lemm.ee
            link
            fedilink
            English
            arrow-up
            4
            ·
            edit-2
            8 months ago

            The entire article explains that’s how it works. I’m sorry it’s just over your head.

            • A_Very_Big_Fan@lemmy.world
              link
              fedilink
              English
              arrow-up
              1
              arrow-down
              3
              ·
              edit-2
              8 months ago

              Mhm, I’m sure that’s why you couldn’t find a single sentence about compositing images

              DALL·E 2 uses a diffusion model conditioned on CLIP image embeddings, which, during inference, are generated from CLIP text embeddings by a prior model.

              You’re either projecting or being dishonest

              • gregorum@lemm.ee
                link
                fedilink
                English
                arrow-up
                3
                arrow-down
                1
                ·
                8 months ago

                Correction: you do not comprehend what you are cherry-picking. Your ignorance and failure to understand to not make you right.

                • A_Very_Big_Fan@lemmy.world
                  link
                  fedilink
                  English
                  arrow-up
                  1
                  arrow-down
                  2
                  ·
                  8 months ago

                  If it’s cherry-picked it should be easy to give me a single sentence, but apparently you can’t lol

                  • gregorum@lemm.ee
                    link
                    fedilink
                    English
                    arrow-up
                    3
                    arrow-down
                    1
                    ·
                    8 months ago

                    I already gave it to you in a single sentence:

                    “You have no idea what you’re talking about.”

                    Even that was too difficult for you to understand.