|
If you ever wonder why everything made with Stable Diffusion looks the same, it's because it can't generate images that are too dark or too bright. The denoising process involves recognizing shapes and shapes naturally have bright spots and dark spots. If you try to render "sea at night" you'll get some huge, bright moon for example. The "AI artists" using this tool lack the technical and artistic competency to realize this. They didn't write the algorithm, draw the dataset, or train the model. They prompted. They have the smallest amount of creative input into this whole pipeline. 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. 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. Amusingly, you could also just type text in GIMP. Instead there is now something called "flux" that can do text literals. While I see the point in making a prompt interpreter capable of generating text literally, if I were creating something, I wouldn't let an AI randomly pick a font, color, weight, serifs/slabs, etc. for me. These are creative choices in design that make all the difference. Prompting gives the illusion of (creative) choice. You get something that looks good, but "getting something that looks good" is the default state. Anyone can do that. It's the AI art equivalent of drawing a stickman. The prompters just don't realize it because they're comparing themselves to to artists of other media, not comparing themselves to other AI artists. 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. It was cool when AI was able to generate video, just like it was able to generate text. But in my opinion, those are feats of the technology, not artistic feats. The piece itself isn't interesting. It could be any video. Just the fact that the tech can do this is impressive. But it's just the tech that is impressive, not its output. Once the tech can do it once, it can do it every time, so the second time AI generates video is never going to be as impressive as the first time. By the thousandth time it will be as impressive as my ability to send this message to the other side of the world at the speed of light. |
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.