• @CluckN
    link
    English
    367 months ago

    I’m surprised it’s able to make readable text.

    • @[email protected]
      link
      fedilink
      English
      87 months ago

      Image generation models are generally more than capable of doing that they’re just not trained to do it.

      That is, just doing a bit of hand-holding and showing SDXL appropriately tagged images and you get quite sensible results. Under normal circumstances it just simply doesn’t get to associate any input tokens with the text in the pixels because people rarely if ever describe, verbatim, what’s written in an image. “Hooters” is an exception, hard to find a model on Civitai that can’t spell it.

      • @[email protected]
        link
        fedilink
        English
        57 months ago

        I like to post sometimes on the “guess the song” AI communities, but more often than not, the Bing image creator just plast the lyrics on the image making it useless for the game.