Comment on OpenAI’s new AI image generator pushes the limits in detail and prompt fidelity

AlmightySnoo@lemmy.world ⁨9⁩ ⁨months⁩ ago

• Devorlon@lemmy.zip ⁨9⁩ ⁨months⁩ ago

  Here’s an example image from the article.

  https://cdn.arstechnica.net/wp-content/uploads/2023/09/plategirl-980x560.jpg

  source

  • Chozo@kbin.social ⁨9⁩ ⁨months⁩ ago

    from the article

    Well no wonder they couldn't find this example.

    source

    • fmstrat@lemmy.nowsci.com ⁨9⁩ ⁨months⁩ ago

      For a system where the intent is to read, learn, or be entertained (and kill time), people seem unwilling to do the first to accomplish the latter.

      source
  • Quicky@lemm.ee ⁨9⁩ ⁨months⁩ ago

    Was the prompt “Woman from China”?

    source

    • Chariotwheel@kbin.social ⁨9⁩ ⁨months⁩ ago

      The prompt is on the picture in the article:

      A DALL-E 3 image provided by OpenAI with the prompt: "A middle-aged woman of Asian descent, her dark hair streaked with silver, appears fractured and splintered, intricately embedded within a sea of broken porcelain. The porcelain glistens with splatter paint patterns in a harmonious blend of glossy and matte blues, greens, oranges, and reds, capturing her dance in a surreal juxtaposition of movement and stillness. Her skin tone, a light hue like the porcelain, adds an almost mystical quality to her form."

      Why do we need AI creating text, when nobody is reading?

      source

      • Quicky@lemm.ee ⁨9⁩ ⁨months⁩ ago

        Whoosh

        source
    • Aatube@kbin.social ⁨9⁩ ⁨months⁩ ago

      You might want to put it all lowercase next time

      source

      • Quicky@lemm.ee ⁨9⁩ ⁨months⁩ ago

        The next time I make the same joke?

        I reckon I’ll just keep it to myself instead. I already feel ridiculous for having to explain it. Lemmy is harder than real life.

        source
• tonytins@pawb.social ⁨9⁩ ⁨months⁩ ago

  Because real artists struggle with hands.

  source

  • thbb@kbin.social ⁨9⁩ ⁨months⁩ ago

    While there is some truth in this, humans and AI do not make the same type of mistakes with hands.

    Humans will rebuild the topological structure of the hand: 5 fingers protruding from a based and get the proportions wrong.

    AI will rebuild the image of a hand from the 2d appearance of a hand: a variable number of flesh colored, parallel stripes, and improvise from that.

    While both can get it wrong, the errors are not similar.

    source
• ZILtoid1991@kbin.social ⁨9⁩ ⁨months⁩ ago

  Making the context window likely helps with stuff, however it still has the issue of "background breaking".

  source
• lloram239@feddit.de ⁨8⁩ ⁨months⁩ ago

  Seems to be about 50/50, quite a few good looking hands, but still plenty of crocked fingers.

  source

  • AlmightySnoo@lemmy.world ⁨8⁩ ⁨months⁩ ago

    Yup that’s the thing with most of generative AI models, they have no implicit 3D modelling of the world. So depending on perspective, a real 2D image may give the impression that there are 2 or 3 fingers only but the model doesn’t know that that’s just because of perspective.

    source