| > If you ever wonder why everything made with Stable Diffusion looks the same Everything you know is made with Stable Diffusion looks the same because if it doesn't look the same you probably don't know it was made with Stable Diffusion. > The "AI artists" using this tool lack the technical and artistic competency to realize this. No, they don't. It's been a frequent comment in the AI art community and a thing for which the community has sought and produced both in-generation and auxiliary-tooling solutions for from very early on. > They didn't write the algorithm, draw the dataset, or train the model. Perhaps not for the base model, people int he AI art community have done all three of those for improvements to and tools built around the base models and the original code implementation of them. > I do believe AI can be used in the process to create art as it's just an image generator like fractal art, but the problem is most people are going to use AI not as a means to create art, but as an end. Most of the people who are using any tool that can be used artistically are going to use it at the most superficial level. Is that true of AI image generators? Sure. But no moreso than it is true of, say, pencils. > You could fix the problem above by simply importing the image into GIMP and changing the brightness, but nobody does that because they aren't interesting into creating an art piece with a set goal in mind, they're just being entertained by generating dozens or hundreds of images with this technology. People are using AI image generation with a set goal in mind, and people absolurely do import generated images into to traditional image editors for adjustments. Though a lot of the people that really know what they are doing have that built into their workflows, reducing the need to do manual spot correction in a separate editor. > Amusingly, you could also just type text in GIMP. Instead there is now something called "flux" that can do text literals. Image generation models have been able to do text to a certain extent for a while, and improvements in text generation have been a major trumpeted feature of many recent model releases. Flux isn't interesting because "it can do text literals", it is interesting because the community has discovered that it can be finetuned (specifically, that LoRA can be trained for it) that will allow control of text style, similar to fonts. I wasn't aware that GIMP could comform typed text to the implicit 3d shape of the surfaces it is being placed on in a 2D image, though. > When everything is AI, and anyone can generate an image with a prompt, the whole market will be so saturated with this (perhaps it already is at the rate these are generated) that all the novelty will be gone. Probably. So what? Novelty isn't the point in every image people produce. Lowering the cost and effort to produce basically "looks good" images for lots of casual uses isn't, itself, an advance in fine art, sure. But it is, in itself, useful. |
What you misunderstand is what "looks good" means. Before AI, art that looked good was valuable and impressive precisely because few artists could produce it. It was amazing (and it still is) that a human being can reproduce realistic or surrealistic imagery with just pencil and paint.
If anyone can do it with one click, there is no value.
Like I said before, you're using AI art and comparing it to other media, like pencil and paint. That's like comparing photography to pencil and paint. Just because photography is more "realistic" that doesn't mean people will value a photo more than an artist's realistic rendering of the same thing.
When AI just looks good, that is actually the most worthless possible thing, as valuable as a sketch of a stickman.