French immigrants are eating our pets!

  • vithigar@lemmy.ca
    link
    fedilink
    arrow-up
    2
    ·
    13 days ago

    I’d expect that many images are going to be somewhere near 50% grey if you average their luminance out overall. That’s just the average of every colour though. The fact that averaging a range of things tends toward a standard distribution isn’t particularly surprising. Again though, it’s not hard to get a diffusion model to generate something outside of that expectation.

    Prompt: “night sky”

    Image:

    Average colour:

    Average brightness: 21%

    Prompt: “lineless image of an old man drawn in yellow ink on white background”

    Image:

    Average colour:

    Average brightness: 90%

    • Krauerking@lemy.lol
      link
      fedilink
      arrow-up
      1
      ·
      edit-2
      13 days ago

      Ehhh you’d be surprised how much small highlights and true dark values will skew an average. You don’t really get blown out or completely under exposed parts of AI generated images. It keeps trying to add some saturation.

      I will say I’m getting different brightness levels than you are but it’s not a big deal. Point made.

      However I will say saturation is also pretty much 50% across the board for all the colors so maybe there is something there to use as an indicator. The average color always comes out grey toned somehow.

      Testing it myself has been pretty spot on.

      Just to point it out, here is a photo I took to mimic the red man. And the color average from it.

      It doesn’t even have the highlights of the face and yet it’s already much brighter and has a much higher saturation.

      • vithigar@lemmy.ca
        link
        fedilink
        arrow-up
        2
        ·
        12 days ago

        Also, this is tangential to the rest of our conversation, but I appreciate the dedication to the comment chain required to actually set up something with similar composition to the red man image and take a picture of it. Even has some black in the image in roughly the same size and area as his sweater. :D

      • vithigar@lemmy.ca
        link
        fedilink
        arrow-up
        1
        ·
        13 days ago

        I’m not sure what you mean by the saturation being around 50% across the board. If I peek the HSB of all of the averages only that first teal-ish one appears to be around the mid point for saturation.

        • Krauerking@lemy.lol
          link
          fedilink
          arrow-up
          1
          ·
          13 days ago

          When I look at the HSL of those colors I get 60, 54 and 46 (ignoring the ocean one cause I just don’t have that open anymore) for the S (saturation) value.

          Like I said it’s weird that we are getting different values cause your brightness also wasn’t in line with what I had. And that wouldn’t be a screen issue.

          My red came in at 73% for me.

          • vithigar@lemmy.ca
            link
            fedilink
            arrow-up
            1
            ·
            edit-2
            12 days ago

            Odd. I tag your red at 78%. And for what it’s worth this RGB to HSV converter agrees with that number taking your colour hex as C92D20. I certainly don’t know enough about it to offer an explanation as to why it might be different.

            edit: Ah, I think it’s HSV vs HSL, which I’m just now learning are different things. :D

            • Krauerking@lemy.lol
              link
              fedilink
              arrow-up
              1
              ·
              13 days ago

              I am importing mine into a photo editor so might be something with that. Anyways.

              Thanks for the examples. It gave me something to think about and the discussion has been interesting. I think there may be details to take away from this but I’m not in a rush to dip back into AI images.

              • vithigar@lemmy.ca
                link
                fedilink
                arrow-up
                1
                ·
                12 days ago

                For what it’s worth I agree that AI images will generally have “tells” that give away their nature. It’s just they aren’t quite so straightforward as being able to check that average values are within a range. It would be nice if it were that easy though.

                While I do dabble with AI image generation I’m not a lunatic who calls themself an “artist” for doing so, nor do I think being a “prompt engineer” is any kind of expression of creativity or skill. I think the people who do are completely self-deluded.