cross-posted from: https://programming.dev/post/3974080

Hey everyone. I made a casual survey to see if people can tell the difference between human-made and AI generated art. Any responses would be appreciated, I’m curious to see how accurately people can tell the difference (especially those familiar with AI image generation)

  • NessD
    link
    English
    49 months ago

    The avocado had real text. Is Dall-E 3 capable of creating legible text?

    • @[email protected]OP
      link
      fedilink
      English
      49 months ago

      Yes, it’s the only model that manages to get text right, and the results are usually pretty consistent. It’s a big step forward.

      AI generated photo of a cat saying "I'm king of the world!"

      • @[email protected]
        link
        fedilink
        English
        0
        edit-2
        9 months ago

        Base SDXL and SD1.5 with the help of controlnet can both do text too. I forgot Deep Floyd/IF can as well.

        • FaceDeer
          link
          fedilink
          29 months ago

          Control nets are kind of “cheating”, though, they’re a form of image-to-image where you provide them with something to trace over or otherwise guide them. I think in this area the open-source field has (briefly) fallen behind, we’ll need another round of catchup. That’s fine, though. Let competition drive hard.