A fascinating genre of AI-generated boomer art is crystalizing on Facebook before our very eyes. Ben Garrison is going to be put out of work. Another casualty of the AI revolution
Show
Show
A fascinating genre of AI-generated boomer art is crystalizing on Facebook before our very eyes. Ben Garrison is going to be put out of work. Another casualty of the AI revolution
Is it just me or is AI art getting worse with time
There's too much AI art on the internet now and it's getting fed into the models so now AI art is literally getting inbred
it doesnt help that this is being used by uncreative boomers to paint tasteless crap.
This is actually the biggest problem. It's boomers coming up with the worst ideas of all time. It's gotten a lot better at making things that could reasonably happen, but these boomers are just coming up with the worst possible images to generate, and because there's nothing even remotely close to that in the data set, it has to hallucinate harder. You can make a picture of guys playing baseball pretty easily because there are lots of pictures of guys playing baseball. Harder to make giant bibles being moved by cops because cops never move anything on their cars, and there's no such thing as a giant bible.
Oh yeah?
The bibles waved about grow bigger each time a fascist coup happens, maybe the next lurch at Bolivia's lithium deposits or Venezuela's crude oil will be as big as the AI image ones.
That is like 5% the weight of the Codex Gigas
The Codex Gigas is the largest extant medieval illuminated manuscript in the world, at a length of 92cm.
Cool.
It unironically has simulated mad cow disease
Huh, suddenly Digimon makes more sense.
It got significantly better, year ago there was no chance for anything even remotely readable and now you can sometimes get few words ok, like in the second pic. Also people on those pics have nearly correct number of limbs and fingers unlike before.
This looks like some SDXL checkpoint, maybe even the base version, so that'd be last year's big hobbyist local model. A midrange graphics card from a few years ago can churn out several of those images a minute, and a high end current gen card could bring that down to around a second (even less for SDXL Lightning).
This is probably the result of a completely uncurated spambot that's just trying to dump SEO shit into a prompt and post whatever comes out the other end. Like literally one single machine could be providing these images for dozens or hundreds of different spam bots because the local models make a local server that can be communicated with via an API by a GUI frontend or other applications.
Edit: checking popular SDXL checkpoints, I think it may be an older version of juggernaut XL, like the bot farm operator just grabbed the top ranked checkpoint from civitai a few months ago then just set up the bots for it and hasn't bothered to grab a newer one or fix any issues - why bother, when the whole thing is some baffling scheme to grift ad views from what seem to be entirely other bots.
It looks like Dall-E 3/Bing image creator to me. It's probably the most accessible and therefore the most used for this sort of thing, especially for weird chudposting
why do you think it's juggernaut XL specifically?
I just went and looked at the top rated SDXL checkpoints on civitai, and that's at the very top of the list and has a similar sort of plastic sheen to it. But after posting that I thought about Stable Cascade, and that both has an even more pronounced sheen like that and similar text adherence to some of the images, but that would be a weird one because it's more complicated to run and not particularly popular.
Someone else suggested it could be dalle, but I don't know anything about the quality or prompt adherence of remote proprietary models so I can't comment on that. The combination of them being strictly SFW and clearly entirely uncurated could point to an aggressively censored corporate model, especially if it was something with a free tier that bots could be querying themselves.
If part of the feedback it gets is positive interactions on social media, facebook boomers might be actively contributing to this lmao
It looks better if the person writing the prompt has several goes at it, refines the idea, and picks the best one. But Shrimp Jesus is spreading so fast that the people(?) writing prompts are just giving it one go and posting whatever it throws out.
The lack of taste doesn't help either.
I have a new theory: American Christians want to pretend that they have read the Bible, but no one can make it past, like, Leviticus. So instead, they just really double down on the first part about creationism, hating women, and wars of genocide committed by the chosen people that they did read and extrapolate that for the whole book.
That's almost a kind theory compared to the alternative: they read all the parts about Jesus being kind to the poor and hating on the rich and consciously chose to reject it.
I knew a Mormon girl growing up who did take it very seriously and had read the Book of Mormon, The Bible (KJV), The Doctrine & Covenants (by far the most interesting Mormon scripture as it is the revelations of Joseph Smith alongside Mormon history and up to his death. Actual ‘prophetic’ ramblings of an Uber-American weirdo conman) cover to cover several times.
She told me the hardest part by far was the Old Testament outside of Genesis and Exodus and a couple others because it was insanely convoluted and boring. Just mundane rules and boring lineages and that kind of thing.
HDOLX
BIBBIE
_ T . T . T
POICE
it's actually pronounced "po-wees"
Taxi
Incoming copyright claim from some crypto bro who wrote "The HODL BIBL"
Call the Pus.
deleted by creator
T Swift's rider has gotten a little weird overtime
Pigs would protect the Pus Taxi
Every car is a Pus Taxi when it has a pig inside, CMV
Pus Taxi? Is that for dairy products?
Gross joke
"Pus Taxi" is what you get when you cross Fake Taxi with pimple popping videos
Do you think people who like this shit just see the world this way to begin with? Like, pure vibes and quasi-surrealist blending together of figures and concepts?
honestly, if u swapped this for a group of soviet soldiers unloading a comically large das kapital, it would’ve gotten a like out of me
We do be enjoying things that are comically large
it's a bit disconcerting to think about (and I don't believe it's right) but sometimes I feel like there's a portion of the population whose brains overcorrect sensory input to a massive degree, where even a crudely drawn image looks like a masterpiece and it really says "POLICE" and "BIBLE" on that AI picture and you would have to walk them through the image step by step in person to explain that
Can we make pus taxi an emoji?
Let’s make Pus Taxi a band! I would totally go see them.
Why are they bound on both sides? Oh, that's right. Bibles aren't for reading anyway.
Haha looking at the soldiers loading the comically large us army edition of the holy bible into the truck most of them don't have hands
ĥ̵̨̦̱ď̵̛̠͎̹̞o̵̲͛̽̐t̸͚͔̲́̈̃̒x̷͇̞̽ bibbie
Me in May 2024 (my best year) riding the PUS TAXI with a comically oversized and literally unopenable Bible on top
Also when all is said and done, I think we can all agree that AI image generation has given us lots of great inspiration for fake writing systems for conworlds.
Honey what’s wrong you’ve barely even read your Bibbie
gender-swapped st. christopher in "poice" uniform carrying ai-generated eldritch horror translation of the bible in place of baby jesus is a take i suppose
i wonder if intentionally spelling wrong when you want text in these things would make it more likely to spell correctly on the output
i just know its because these boomers are just typing the words "bible police" into the prompt and going with whatever pops out.
i would take pus taxi tho.
Actually it seems like an iterative system of making images based on those that got traction previously. For example, I saw the Drew Gooden video and it was clear in that that these AI things seem to get more and more specific with time, so it could be that these programs are using engagement as the positive reinforcement to find and refine their AI images, prompts, and text descriptions into what gets the most engagement possible
okay that actually makes a lot more sense