When Adobe Inc. released its Firefly image-generating software last year, the company said the artificial intelligence model was trained mainly on Adobe Stock, its database of hundreds of millions of licensed images. Firefly, Adobe said, was a “commercially safe” alternative to competitors like Midjourney, which learned by scraping pictures from across the internet.

But behind the scenes, Adobe also was relying in part on AI-generated content to train Firefly, including from those same AI rivals. In numerous presentations and public postsabout how Firefly is safer than the competition due to its training data, Adobe never made clear that its model actually used images from some of these same competitors.

  • General_Effort@lemmy.world
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    35
    ·
    7 months ago

    No.

    I feel I should explain this but I got nothing. An image is an image. Whether it’s good or bad is a matter of personal preference.

    • hyper@lemmy.zip
      link
      fedilink
      English
      arrow-up
      36
      arrow-down
      1
      ·
      edit-2
      7 months ago

      I’m not so sure about that… if you train an ai on images with disfigured anatomy which it thinks is the “right” way it will generate new images with messed up anatomy. It gives a feedback loop, like when a mic picks up its own signal.

      • General_Effort@lemmy.world
        link
        fedilink
        English
        arrow-up
        7
        arrow-down
        5
        ·
        7 months ago

        Well, you wouldn’t train on images that you consider bad, or rather you’d use them as examples for what not to do.

        Yes, you have to be careful when training a model on its own output. It already has a tendency to produce that, so it’s easy to “overshoot”, so to say. But it’s not a problem in principle. It’s also not what’s happening here. Adobe doesn’t use the same model as Midjourney.

      • abhibeckert@lemmy.world
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        6
        ·
        edit-2
        7 months ago

        Midjourney doesn’t generate disfigured anatomy. You’re think of Stable Diffusion which is a smaller model that can generate an image in 30 seconds on my laptop GPU. Even SD is pretty good at avoiding that, with decent hardware and larger models (that need more memory).

    • bionicjoey@lemmy.ca
      link
      fedilink
      English
      arrow-up
      4
      ·
      7 months ago

      When you process an image through the same pipeline multiple times, artifacts will appear and become amplified.

      • General_Effort@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        3
        ·
        7 months ago

        What’s happening here is just nothing like that. There is no amplifier. Images aren’t run through a pipeline.

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

            Yes, but the model is the end of that pipeline. The image is not supposed to come out again. A model can “memorize” an image, but then you wouldn’t necessarily expect an amplification of artifacts. Image generators are not supposed to d lossy compression, though the tech could be used for that.

            • Grimy@lemmy.world
              link
              fedilink
              English
              arrow-up
              6
              ·
              edit-2
              7 months ago

              If the image has errors that are hard to spot by the human eye and the model gets trained on these images, thoses errors that came about naturally on real data get amplified.

              Its not a model killer but it is something to watch out for.