I was on stable diffusion art and one of my comments got removed for saying the OP didn’t “make” the AI generated art. But he didn’t make shit the AI made it, he typed in a description and hit enter. I think we need a new word for when someone shared art an AI made, like they generated it or something. It feels insulting to actual artists to say you made art with AI

  • bishbosh@lemm.eeEnglish
    2·
    4 hours ago

    you can put the exact same prompt into the stable diffusion and not get the same image each time

    My understanding is that if you have the exact same model, prompt, and everything else, if you use the same seed, you will get the exact same image output. That and that they called it a counter point, I took it to mean they were talking about the skill in the layers of different tools folks will use to get what they are hoping for. Because, a little to your further point, there are folks that get very into it and have like 30 different fine tuned loras or whatever to finesse every finer point of the image.

    Images would not exist without the photographer choosing to make them.

    At the risk of getting a little philosophically wanky about it, I guess I would argue the same for AI images. Like what exists is a nebulous connections of weights and nodes trained off stolen art that only connect in certain ways because of a given seed and prompt. Does a hypothetical random image of a muppets version of Kermit the frog as Darth Vader ‘exist’ without the high, half baked, prompt from someone using a free trial of midjourney?

    Even without those elements though, those images would not exist without the effort, intention, and presence of the photographer.

    I completely agree, and I think my point more was that with photography, you don’t “make” the landscape or architecture you’re capturing, but you make the image in the end.

    Contrast that with AI art. The only intention you have is your prompt and choice of model. I would argue the fact that ai prompters need to “get close to” what they want their piece to say, rather than making the piece say what they want it to say, shows how starved for meaning the products are.

    I will say, I respect photography more, and so much of what AI generates is soulless slop. I think that ultimately my push back is on the folks that argue that it can’t be art. And just as there is intentionality in choosing what photos you don’t take for photography, there is non-zero intentionality in generating 30 loose candidates, 50 fine tuned candidates, and 3 final images with stable diffusion.

    Sorry if this comment is scattered, I’ve restarted my reply like three times trying to sort out what I even think lol.