This is not a bit holy shit, I looked at this guy's account and this is genuinely what they do. https://twitter.com/OpPainkiller/status/1736078240073011555
It’s the combination of the massive lower half, complete with the belly/thigh “cleavage” that chubby girls get, but also having a six pack that’s a different color than the rest of her skin that’s just
The tiny T-Rex arms, combined with the T-Rex in the background...kinda amazing, ngl
Only super advanced prompters know how to properly change the six pack's color
That seems to be the default face these AI art programs have for any anime-related prompt. Which says a lot about their database.
But there is no skill or experience here
This looks exactly like all the other AI art of women with massive tits I've seen being touted as "revolutionary"
I guess if you're so cum-brained that this does it for you, but seriously, some of us have standards
But there is no skill or experience here
Even setting aside the grotesquerie of it all, you can't help miss how much of the image is stapled together. The petite head and arms attached to an enormous torso. The... six-pack abs in between balloonish chest and thighs. The poorly rendered blandly colored dinosaur in the background. Meteorites falling in from different angles for no discernible reason. Oh, but hey, they did shading and texturing reasonably well on the primary model, woohoo! Art!
Like... there's no story here. Its a confused jumble of adjectives even before you get into whatever prompt they used to produce this.
I guess if you're so cum-brained that this does it for you
You can be cum-brained and this still looks like shit. And in a period of time that's never produced more porn by volume or category, it seems absurd to rely on AI for images a catalog of dirty sci-fi pop magazines from the 1980s had in abundance.
With enough practice, you too can design an unsettling sexual homunculus being chased by a dinosaur!
I'm most offended with how the lyrics don't match the song's meter
The weird fetish for insanely large breasts is what turned me off from cartoon porn. Or I uh - I mean turned my buddy off, sorry officer
Right? It's really grotesque. There's like real human huge, and then there's anime medium. Which is like 10x the size of real human huge.
If I were this guy I would simply not bring up fetish art to make this particular point
Looked at the account and when you said "this is genuinely what they do" you did mean it, jesus
Taking off the
hat for a moment: If you're going to use AI to pump out low-effort wankbait, at least be good at it. That objectively looks fucking awful.If you can describe this picture, you can get an AI to make it. There is undoubtedly some nuance to crafting AI prompts, but unless you're looking for something super duper niche and specifically hard to describe (and you're willing to trawl through 10,000 failed attempts by the AI), it doesn't really matter and you're probably better hiring a human still anyway.
The hyper booba butta art is for sophisticated gentlemen, hexbear wouldn't understand.
Am I misreading him, or are his statements not even internally consistent? You can make quality art in any medium without skill, but also neither a beginner not an experienced user can make quality art in this medium?
I think what he’s saying is that AI isn’t just a magic art button, and that while amateurs can get good results, that’s true of any medium. An amateur painter or graphic designer can get passable results without a great deal of practice, but in order to get truly excellent results, you need to put in the time and effort, and that AI art is no different.
This level of huge, round, juicy boobs and thighs is only achievable by the most skilled and experienced AI prompter.
I'm pretty sure they are saying that this piece of... well, let's just say this "piece", wasn't created by prompting. They are trying to place themselves above the most proficient prompters.
Which infers that they used methods that give the creator more control, such as ControlNet. ControlNet makes a structure for the generative AI to build on, which means you can guarantee certain features appear in the final output. So you could, for example, reskin a real building with fantastic imagery while retaining the building's original form.
But unless someone is capable of tailoring their own ControlNet-style software, they're still really just a script kiddie. (In this case, a script kiddie with no taste but a lot of problems.)
Of course, you could also train a LLM to utilize ControlNet settings solely through prompts, since LLMs allow us to use our own personal vocabulary as a high-level Natural Language Programming language. However script kiddies are fundamentally reactionary in their own right. They aren't good at thinking for themselves (or perhaps at all). They will eat what is put on their plate, but if we place them in the kitchen then we will surely all starve.
Of course, you could also train a LLM to utilize ControlNet settings solely through prompts, since LLMs allow us to use our own personal vocabulary as a high-level Natural Language Programming language.
I really don't understand what you mean by this. It sounds like a very inefficient way to use controlnet. What settings would you be tweaking with an llm? Why would you use an llm for that, instead of a slider/checkbox?
I wouldn't do it lol. But you could create a workflow in which you could make similar products using only prompts and some custom tooling.
The creator of this piece said that it can't be made by a prompt. What they are insinuating, is that different inputs make their outputs more or less superior. But that's such an arbitrary and ignorant argument when you come at it from the view of LLM product design.
It used to be that parameters were input at the command line. Obviously this becomes impractical for mature use cases, so UI frontends were created to give us sliders and checkboxes. That matches the kind of environments that they are already using. But these are also typically power users (by interest, not necessarily competency) and we've seen a new iteration of UI designs for consumer LLM products like Dall-E and Midjourney. Just because the LLM has a user-friendly skin does not mean the functionality is any less capable - you can pass parameters in prompts, for example.
But if you were to have a use case for a product that uses ControlNet with only prompts, like I said, it would benefit from extra tooling: Presets, libraries, defaults, etc. With these in place more powerful functionality would be more quickly accessible through the prompt format. I'm not Nostradamus, but one area in which simpler inputs are much more desirable than power user dashboards, is in products that are intended to be used by drivers (not all of which are related to the act of driving itself - like voice2text messaging).
I guess my point is that the argument that "my sliders are better than your prompt" is like saying the back door gets you into the house better than the front door, it's really nothing more than a schoolyard pissing contest that shows a limited perspective on the matter.
I think the reason they specified "advanced prompter" is because just text to image (supposedly) couldn't get you this image. If you want good images, you need to use more then just prompts. Using image to image (feed the AI an image and prompt) is a basic example. There's controlnet to give it a scetch or depth map. Photoshop and other "traditional" image editing tools are also used.
But this is a garbage example, obviously.
