Have you considered making the model leverage computer use via Work/Codex?
I'd imagine making the agents use the same tools that people utilize would greatly dial back how AI-generated these things look, and it would provide much better control too.
With Astra being genuinely much better at this, it should be more viable than ever.
every one of them still reeks of AI. especially the trend of icons next to the activities (tombola etc). its just a reskin but they all look AI, just not that triggering minimum effort AI look that is everywhere.
What do we loose when we ditch generative AI? Easier poster making? What good does that do? So now pop&mom can have a poster in their shop that looks as if some graphic artist was paid for it, but wasn't. Will that drive the economy up? Improve poverty? Halt the war? Make life more tolerable? No, it just adds the pretense of having a professional designer, something that will quickly loose its added value when everybody does it.
That's true. Since ornamentation is effort-signaling, it may get dropped once it's cheap. Same thing that happened with clothing and home decor. The functional part may be beneficial though, even on utilitarian grounds. But yes, a lot of design is not about function but social signaling of taste and money as well as fashion.
This feels like an AI trap almost. A lot of the badness comes from people who don't want/can't put effort into it, so we all get a deluge of the sameyness.
Or is it? Could it be the well established low-effort tendency when the dominant culture is shopping centers, vehicles, similar eating establishments, and the style of suburban housing to a large extent? That would surely encourage the LLM to emit in a similar manner. That sameyness provides a signal of comfort and familiarity.
The author claims that the AI posters don’t have to be horrible, but fail to see that the dozen variations generated are not distinctive - they might have somewhat different typography or imaginary, but still have the same AI uniformity and smell as the crappy restaurant poster you see on the street. The core issue is not only technical, but also the lack of vision and imagination when creating art or even infographics.
The alternative is WordArt, or just black on white Comic Sans with some bolding and font size variations with bad ClipArt. These small scale events would never hire a professional.
I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
I see the chatgpt poster style on many small-scale local village events also. But again, what they replace wasn't any better. It's not replacing some beautiful craft that existed before.
God forbid some overworked volunteer make a poster in 30 seconds instead of taking a college course to please some huffy internet commentators with an axe to grind
In the examples above, that’s really your own loss? There will only be one or two events in your local village, it seems self defeating to ignore what they offer because you don’t like the medium. At least these posters are well laid out and easy to read.
I am somewhat tired of all the AI posters, but I have to agree with what you are saying. The alternative was not any better. I think there's a persistent and very vocal segment of the population that just want to complain about anything to do with AI with a take no hostage approach. Some instances are understandable but if a local small town event or a low budget restaurant using AI to make a poster draws so much ire, I feel that it may be likely misplaced personal frustrations projected towards others. The response don't seem to be proportional to the offence.
> I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
We basically had two kinds of posters:
- those made by someone skilled/savvy (not necessarily a professional)
- those made by someone without skills/knowledge
The later were awful, in the sense that I would never display them in my home as a reminder of a an event I took part in.
But still, they were nice because you knew someone took the time to create them to promote an event and share the important information about it, and each person was producing their own awful posters.
Now with gen AI we have something filled with trash, everything looks the same, the important information is hard to find...
Sure, the variations offered in the article are a bit better and more opinionated, but they still reek AI conformity and I feel sick looking at them.
Yes. That's the issue: we are looking at the same posters.
It's just that "seeing this poster for the first time, unaware of the workings behind it" is a very different experience from "seeing this poster after you already saw dozens of other AI generated posters that used a similar style and had similar issues, got canny at spotting both the style and the issues in it, and came to associate them with cheap low quality work".
The former impression is "wow that's a good poster". The latter impression is "ew, it's posterslop". The poster, in the meanwhile, remains the same.
AI can often win in art contests - images, short stories, design. But that requires either sharp prompting, or an audience that's not familiar with "AI cliches". The quality is, if removed from the context, fairly good. If embedded in context, it's utter slop. The work is the same. Funny how that works.
If you think about whether it is AI, are good at recognising those tells, an thinking about whether it is AI, then its probable you will spot things like that.
Most people are not that good at spotting those tells, and when looking at a poster they will not be thinking about whether its is AI or not. If its not obviously AI they are not going to even think about it.
If I saw an Images 2.0 flyer in year 2020? In a world where Images 2.0 didn't exist? I'd be impressed. But if I see it now, today? I'm not impressed at all.
It's the same image, produced by the same AI and seen by the same person. So, what's the difference? What changed over time?
Saturation. "I've seen it all before." AI made that specific flyer style plentiful and omnipresent, and that made it "derivative" and "cheap". What used to invoke "cool" and "wow" was turned into a dreary cliche by repetition. Flaws that were easy to overlook when overshadowed by novelty stand out like a sore thumb now that you've seen them before in the same patterns many times over.
The image is the same - it has the same strengths and the same flaws. But your focus is shifted by familiarity.
It's the same mechanism that drives trends and fashion. AI just supercharges it.
Naturally, you can avoid a lot of it by using careful prompting and steering to guide an AI away from the "cliche" style-space. You can get something with both good quality and good identity that way.
But that requires: being aware of the problem, being really good at prompting, and putting in a considerable effort. It's hard to steer a model away from "AI cliches" if you don't have the eye to spot them in the first place.
Most AI-generated content doesn't have that kind of skill and effort applied to it - it simply uses the "model defaults", and gets the "model defaults". For all the good and bad that comes with those.
Some level of uniformity is fine and indeed the norm. It was uniform back when posters were hand painted, eg 19th century world fairs or zoo openings or theater posters. They look pretty similar. Carneval posters looked similar.
The expectation of some kaleidoscope of styles is not really grounded in how things used to be ever.
Also, it's just nostalgia, just like how some young people now think audio cassettes and discmans are "cool" and have some revival, some are nostalgic for the back-in-the-day Word posters because "at least back then", but "these days" it's decline etc. Pretty sure in a few years people will be nostalgic for crappy AI slop of 2025-26 because their shittiness will feel like some charm compared to whatever the AI will be able to do.
I'm not sure about that. I, myself, am not skilled enough to make a nice poster, so when I needed one, I used to asked my skilled friends to do them for me.
But sometimes I also purposefully made myself some Comic Sans stuff, exaggerating them in every possible way, as a joke. And it was well received because people knew it was my own work and understood the joke.
If I made this today, it would not be seen the same. People would thought I'm trying to fight gen AI trash or I'm nostalgic of the past. While I'm just trying to make a joke by making something awful on purpose.
And I couldn't do the same joke using gen AI. The "on purpose" cannot be conveyed. People would just see gen AI trash.
Making stuff that's bad on purpose is annoying, like acting retarded ironically. Make good stuff or just spend little effort. Putting in effort to look low effort is just trying to be special when you're not.
I was one of those "skilled friends" that people go to, to make those posters in times of need back in school. And this was many years ago. Didn't enjoy it, but just did it as part of volunteering, or help the student community or a school club out.
Some people enjoy doing that work, but most people did not, and I was often the last resort because a random club or activity could not find suitable help in time. So had to step up when a friend or acquaintance asked.
I think there is some misguided view where in "the good old days" people designed everything by hand. From the perspective of someone who had to make 10-20 of those a year as a volunteer, I can say it came at personal cost, often caused distractions from the actual event, and there was not enough people who stepped up to get it done. If it was so enjoyable we would have no problems finding people doing the work and that was not the case.
The posters and designs were often rushed out late night by the closest person you can find who had a copy of photoshop on their computer. If we had AI back then, I would bet you 100% it would be the preferable solution and no one would bat an eye. It wasn't the type of work a lot of people wanted to do, could do properly and is willing to do for free, at their spare time, rushed for a deadline.
Sorry, but Walkmans and Discmans were considered cool... At the time.
Personally I like simple designs. I always remind people who make posters that whoever looks at them will only do so for a matter of seconds. If you want extensive detail, put it in smaller print. Put the main hook in large letters and a brief description.
But they became uncool when the iPod and mp3 players came out. Nobody felt sentimental about VHS artifacts either, and now it's a genz aesthetic or something. These things cycle, like I'm sure some old folks miss the radio hiss and listening to football matches with just audio.
If you read the article at all, the "everything looks the same" is easily fixed with just a tiny bit of effort.
It's not AI causing the sameyness and hard-to-read nature of these posters, it's people being lazy. I personally think there's a few nice looking ones in there (the punk fanzine style for one).
Sure it's not some 9/10 hand made poster, but considering these take 30 seconds to make, it's impressive.
The variations the author generates are night and day better than the "piss filter" era slop in the first batch.
Some of them would have passed as intentionally crafted by a graphics designer before AI.
And let's not forget that before AI, many of these would be word doc printouts with clip art. The alternative wasn't hiring a designer - the alternative was doing nothing special at all.
I was honestly ok with the silly looking posters. Where I'm from in italy it's common to have sagre, sort of cheap food events sponsored by the municipality/local shops. Before ai the posters looked like each other (as in, poster typically looking like sagre posters). Now not even that, they're just slop ai that could be everything before you read. Nobody needed better looking posters in this case...
For me what always gives it away is not the posters themselves, it’s the context. These are all overdesigned for a local community fair. There is no way they’d be paying for a professional designer for this, therefore it’s AI.
On the other hand if it had word art, grammar/spelling mistakes, images with wrong aspect ratios or clipping issues, that would immediately convince me it wasn’t AI.
but fail to see that the dozen variations generated are not distinctive - they might have somewhat different typography or imaginary, but still have the same AI uniformity and smell as the crappy restaurant poster you see on the street
Hard disagree: every single example TFA gives is way better than the horrible generic ones that are polluting every shop and LinkedIn post.
That's not what OP is complaining about. The issue with AI art isn't how the individual piece look, but the similarities they have in aggregate. One image can look perfectly fine, once you seen a hundred they all start looking extremely similar. Human brains are great pattern recognizer and lock on to those similarities, even when they are covered under different styles.
When all your art comes from a single source, it's difficult to create real diversity and novelty. That's still the big issue when it comes to genAI in general, without a lot of hand holding you'll just bound to end up with slop, since the AI won't get creative on its own.
I am not sure. If something is not in the usual AI style its not going to leap out at you that it is AI the same way. Maybe if thought about it, but when someone looks at a poster they typically focus on the information, not the style.
Did you look at the examples? They're almost ridiculously diverse, and the prompts show very little handholding was required.
They're not novel, but a poster for a spring fair isn't supposed to look like a de Kooning.
These arguments are almost completely detached from reality. Most artists aren't diverse either - they're told to find a style and stick to it, and that's what they do.
Commercial graphic designers are more versatile, but the set of standard looks is still relatively small. Hollywood movie posters and book cover designers are notorious for reusing the same tropes and colour systems, and that's been true for years, long before AI was a thing.
t still have the same AI uniformity and smell as the crappy restaurant poster you see on the street
You have really try hard to see that. It is good enough to not give immediate annoyed reflex of seeing something in the same ubiquitous default chatgpt style.
For goodness sake - these are just a fair posters.
Idk, those are more than alright to my eye. Surely they won't win any design awards, but as a throwaway poster for one time event these are miles better than any amateur work.
It doesn't fail, it actually demonstrates how the model can improve the output if the prompt is better. AI generated websites look like crap because developers don't know any design language so they have no idea how to prompt the models to get something good and more unique and creative out of them. This shows that you can actually achieve that with just slightly better prompting. Just like with programming, actually.
Designers republic and memphis were the only designs i couldn't immediately see were AI generated.
The only reason i couldn't tell memphis is because it's aping a known design language already, it's just a perfect copy so me not being able to tell it wasn't AI isn't a free pass in this case.
I think if there was a little less "grid" feeling to the layout details then i wouldn't be able to tell on a few of the other designs either.
Edit: the designers republic version is quite a lot different than the others, it's not just that it's the only design to avoid pairing every feature with an icon, it's the whole layout variety - there's different font sizes, the positioning of elements is very well done to my eye. I'm gonna say this has to be another case like memphis, there's some pre-existing design language that i don't know of and it's just aping that. It's much more human than the others which i can believe are straight ai.
But the thing is, all have that icon+text style in the "tombola, cakes and drinks..." part. If I wanted to be distinctive, this is what I would have tried to get rid of at first, not the "visual style" (it's sort of like Windows XP visual styles, no matter how different they are the overall layout is still recognisably Windows).
although I guess it's that the author used the same context with the original generated image and thus it just reused that icon+text thing
but in general, these models do seem to be kind of just go for an information-dump type of style where its just listing everything and putting as much stuff in that is associated with the words, which is what these LLMs do
so you'd probably need to steer them heavily with explicit instructions on what to do and how to get rid of it, which I'd bet nobody will actually do when making these posters
It’s not complicated - the default style signals low effort. Why should I get excited about the village fete if the organizers put in the barest minimum of effort?
But there’s another reason it drives people crazy - it’s low effort trying to present as high effort. If the sign was simple Comic Sans then it would at least be charmingly honest.
Why should I get excited about the village fete if the organizers put in the barest minimum of effort?
Because there's no correlation between the ability to organise a village event and the graphic design skills. (Apart from "it's been so successful we can splash money on a design agency") Maybe someone actually liked it and thought it's enough. I've seen groups overthinking posters and it felt similar to groups at uni overthinking funny names instead of doing the work that actually mattered.
To be clear, I'm not saying those designs are good, just that most of the time the design is not the point and minimum effort above "Times New Roman 12pt" is what many people always wanted to do.
Graphic design skills don’t correlate with effort. I’ve seen terribly designed posters that the makers clearly put a lot of effort and love into because they loved whatever it was they were promoting.
I’ve also seen people put a lot of effort and love into poster and stuff because that interests them (doesn’t mean they’re good at it either), then the event is utter crap because they didn’t spend much time on the actual event.
The last paragraph in GP’s comment is the key. Nobody would care about a low effort poster, what they care about is the deception of pretending you put a lot of effort into the poster. It’s dishonest, and it would make me subconsciously question what else they’re being dishonest about.
I think this (low effort posters) rather signals to me that they have the right priorities. A true professional poster would tell me that it's some commercial cash grab instead of real local enthusiasts making something normal.
I am inclined to agree. Small community organisation cannot afford to pay a professional designer. They might be lucky and have a talented volunteer, but in general its a waste of limit resources.
You don't have to get excited by anything. You are welcome to boycott the village fête because you think they didn't put enough effort into their poster. Your choice, my friend.
I live in a village with lots of local events and I do not care about the design of the posters. I just care about what the event. I just want some information.
But if a designer improves an AI design and I feel it's fine, does that make me strange? If you ran a blind test on this, I think it would come out with high preference...
I think this is a misdiagnosis of the problem. The AI posters are just fine, perhaps even pretty good.
The problem is that using AI to create the posters show a lack of willingness to put in effort, and it makes you question whether the producer cares about the product and whether they care about the large scale societal problems related to the usage of post-2022 transformer based neural networks.
Most fliers put together for community events pre-AI were Microsoft Word or Google Docs plus clip art.
The world is getting better, but before everyone realizes it we have to complain first and reminisce about the good old days of Wingdings and Comic Sans.
It’s actually very amusing to me comic sans is being referred to as “charmingly honest” on this forum, of all places. Shows how much this is all just aesthetic judgement and doesn’t have any connection to reality, just opinions. Before, comic sans was so low effort it earned scorn and derision. Now, it’s charming. Meanwhile, it’s actually the same amount of (low) effort as always. But for some reason now it has been elevated. Seen people say the same about MS paint drawings, and that’s when realized this isn’t serious at all.
Everyone is suffering and not getting what they want to some degree. Life is short, and opportunity runs out. People turn this into bitterness and direct it at external things that are going well that they're not a participant in.
It's not just AI, it's everything. Romantic rivals, celebrities, sports teams, fandoms, choice of IDE or programming language.
It's a social evolutionary strategy to neg and gossip about people and things you don't like or are jealous of. It's low energy, has little downside, and can reduce the fitness of rivals, especially when done in group settings.
The algorithm has co-opted this part of our primate brain and turned it into ad dollars.
What's interesting is that you can't do the same with long-form AI prose. You can ask any given LLM to write in different styles, but it will always fall back on the same rhetorical and structural techniques, so the "new style" is strictly surface-level. In fact, it's getting worse over time -- especially in Claude from Opus 4.6 --> Opus 5.
I suspect that the same thing is happening here -- as other comments note: lack of distinctiveness, uniformity -- but that the low information content of posters prevents it from becoming immediately obvious.
The similarity may be partly the image model's fault – especially if it's been post-trained/distilled towards performance, correctness and "quality" (for some value of "quality" anyway) which inevitably occurs at the expense of creativity and variation.
But I think it might be more about the LLM's lack of creativity in coming up with the prompt for the image (or "embellishing" a user's prompt), or directly the embedding vector if the LLM is itself the image model's text encoder. Then whatever the image gen outputs is simply an instance of the GIGO principle. It would be interesting to test whether similar cliches and motifs also occur if you ask the model to create an SVG rather than a raster image.
The Designers Republic one arguably avoids it. Only one of its five is an icon: three are zero-padded numbers and one is a smudge where someone forgot to stamp the icon.
I see, across my city and others I visit, every bar/restaurant/etc now has low effort one shot posters, menus, etc, some with old chatgpt nonsense text / errors. It's everywhere. All that brown-ish hue food 'pictures' etc. I mean 'authentic Pizza napolitana!' and then an AI generated picture of said pizza... One of them (an Italy born Italian restaurant owner here) and he just said; people come in with the very expensive pictures / menus I had before and the same amount of people come in with these free ones. And he actually likes these better as photographing (real, not mcd/burgerking plastic props with poison paint to make it look better) food is hard, even when paid for.
Here in Bielsko Biala (southern Poland) I see the same in few pubs, never seen on menus though. Shops seem to be creating lots of marketing images as well with AI and it just looks...off. In any case doesn't make me want to enter the place.
AI posters are not horrible, they just expose the person who "commissioned" them as trash. In a way, that is a good thing, since you can avoid them more easily.
Their very first attempt is arguably the best one there. I was surprised they didn't like it much and kept going. Then the "Stamp / Letterpress Style (Modernised)" was the only other good one.
So of the two designs made, only two were good, the rest was quite bad and lost all meaning.
It's pretty sad when you realize the average person is just kind of... unaware. They are fine with whatever, they don't really notice most stuff that goes around them.
Most AI-generated art is "good enough" for most one-shot designs by now (though still not [always] as good as a good meat-based artist of course)
The problems right now are:
- Maintaining a consistent and coherent style/aesthetic when you have to generate lots of assets for something. For example sprites in a video game.
- Iterating over a design for more than a few passes. For some reason most models keep degrading the entire image if you keep asking for edits to a specific part of the image. Or, some problems are or become impossible for them to fix no matter how you prompt them.
It's not that the first one is so awful in isolation, it's that they are everywhere you look when you walk down the street. The barbers, the school fête, the cafe, the church. Everywhere.
I like the other posters more, but the first poster probably still conveys the idea of the event better: people having fun, drinking beer, with a live band. You don't get that from most of the other posters unless you first mentally transform those icons into real things, which takes effort.
People dont want to write multiple prompts or write a lengthy one. They want to say create poster x for event y. That's it, that's what they get and that's what they take.
Buried at the end of the article the author linked a library of different art styles applied to the same poster content. Found some new cool art styles to try out in the future.
https://john.hartnup.uk/poster-prompts/
AI is a tool, just like photoshop was. Just because someone bought photoshop didn't mean that they can magically create amazing digital artwork, they had to learn photoshop and also be creative. Otherwise it would have been a horrible poster with comic sans. Same goes for AI, one has to learn to use the tool and be creative.
I think we're in the 'early digital camera' phase of AI art gen.
The real photographers knew they were shit photos. They were grainy, bad lenses, and ugly. A lot of people still liked them because they were much more convenient for a lot of uses than the film ones.
Well, I guess there's still a lot of film people. But film had a ceiling. Digital cameras kept getting better.
The adaptive film photographers eventually adopted the tool. A lot of their skills transferred well to the new medium. Most waited until the cameras got good enough, though.
I'm not sure when that'll be with AI art gen. Seeing scenes broken up into layers in the latest gpt image generation, though, made me think we might be near.
At least the AI generated posters are better than human-generated t-shirt designs, where you find generic texts such as: "Est. 1984" (or any random year), "I [heart] NY", "Property of [City/School] Athletic Dept.", "Original Trademark", "Authentic Denim Brand", etc., etc.
At a certain point, pottery that looked like a child made it became the high end, because well-executed pottery was coming out of machines.
We've officially reached that point with advertisements. Save your tokens. Hire your 9-year-old niece to draw the poster by hand and you'll likely get a far better reaction from most people. Nobody goes to a fair because the poster had a "modernist / Bauhaus-influenced graphic style".
if NOT TRULY personal preference, then all those variations ARE horrible, but if they serve some taste--personal or marketing--then they are likely not to everyone's taste.
to me, they all look like lazy-prompting, which is the only way I ever do genAI imaging, because I fail to see why that "CPU" should be wasted on something I barely even care for.
That said ... let kids do that shit and pay them 50 or 100 bucks ...
The issue is that in my walled garden, I have not seen any of the good AI stuff. My wardens still use some home trained GPT 3.5 for most stuff, including their songs on potify and bootube. And i can't get access to current top level public AIs, either. Had the actual ChatGPT and Claude models for some while but I knew why ... otherwise I might put effort into semantics, syntax, grammar and my image generation prompts, which currently look like some MITM is speedrunning collages using haiku cowork and crayons or something ...
I find it kinda funny that even "smartest", most capable models often have a very hard time going beyond surface-level, top-of-mind associations, when faced with creative tasks.
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.
Sure, but what's interesting is if you tell it to "behave unpredictably" or "don't use tropes" it usually fails down the same curve. Which is predictable, but telling.
I remember seeing a poster for Chinese New Year years ago, and someone had included the kanji for Japan on it (日本). Obviously they just wanted generic looking characters without bothering to see what they meant. I couldn't resist writing a comment on the poster about it.
It showed whoever did it had no clue about East Asia or Chinese script...
But AI has absolutely no problem with going with the cheesiest, most overused trope.
Considering your prompt fits exactly that description I think the AI delivered perfectly. Try using some actual design language and see how well it does.
Isn’t the most overused trope the most statistically weighted to be chosen from a group of options? It makes technical sense but as you say leads to boring outcomes
Is there a way to formalize the space of all possible aesthetics a model knows, in a way that you could randomly sample from it?
The analogy in my mind when I read this post was: you are asking a machine to paint a color, but the machine always paints the exact same shade, deterministically; and you'd like to explore different colors, but somehow you don't know anything about colors, don't know any of their names. So you don't have the language to ask for what you can't name.
Random sampling of colors (without names!) is a solved problem, because we've parameterized the entire universe of colors that can be perceived. It's just a very low dimension manifold, and there's even a computable metric on it such that unit-distances in that metric are what humans say are color differences of equal step size.
Are there more general versions of this? Like: "Here's a list of every human art in history: infer a coordinate system that uniformly metricizes every art that can ever exist?"
Well, sometimes AI generates pictures that are not bad. Personally though I am tired of AI slop in general, and I don't want to support it. AI literally kills humans. In some scenarios AI is still useful (e. g. if you write a game, say, in javascript and you don't have any designers helping you out, you could generate images that don't suck, quickly, via AI) but other than that the less I get of AI the better. Google now has that problem with AI - tons of AI slop and fake videos. I realised the AI slop just wastes my time but Google does not offer a simple "do not show me any AI slop" videos. After all they want people to waste their time on youtube, by design. So I now waste my time twice by using Youtube, if I watch an AI slop video.
But more importantly, if you aren’t the kind of person who could make a halfway decent text only poster before, you are going to make the posters at the top of the article. Those are objectively harder to read than something typed up in word.
You aren’t going to know to tell the AI to “ Go for a clean, unfussy, bright layout with a bold striking spring-themed graphic. Avoid pastel/airbrush/oil style art or images of people.”
The only ones that aren't horrible manage that because they're so bland there's nothing to go wrong. Look at an example with some detail, the "Now please make one in the style of a 90s drum n bass gig flyer, with early 3D/fractal computer imagery" poster.
At the top of the page we have a deformed wireframe sphere. A wireframe sphere is stylistically appropriate, but the incorrect rendering is not. The "CGI" aesthetic requires obviously computer generated lines, which in the 90s meant accurate and regular lines.
Next we have a messed-up stellated polyhedron, and a messed-up dot pattern. These also fail for the same reason. The main 3D rendering is also obviously broken, as are many other small details.
But the biggest failure is the complete misunderstanding of the culture. 90s DnB was absolutely not about "good vibes". The smiley face logo is completely inappropriate; that's associated with late 80s/early 90s rave culture, pre-DnB era. 90s DnB was much darker and edgier in tone. The scene was almost exclusively male, and it maintained a aggressive vibe carried over from jungle.
A 90s DnB event would never advertise "bringing communities together". Audiences would be repelled by such messaging. This is despite it actually doing just that, as the scene was racially integrated in a way that mainstream music at the time was not. If there's going to be pro-social messaging on the poster it has to be there only implicitly.
I'm reminded of how Mac apps are supposed to conform to common UI standards rather than going off and reinventing the wheel. Also the Bootstrap template for websites.
Similarly, it would be nice if there were common styles for posters that you could just use and an AI could generate and nobody would criticize you for. Not everything has to be an original design.
Generative AI is actually pretty good at giving you rough concept sketches and iterating on top of existing renders.
However, you must retain control over the scene graph and its composition. Use the output of the AI to guide how you work it. Do not assume the AI system has the ability to simulate world space with any meaningful fidelity. You can move transforms around in Blender and Unity with floating point bit increment/decrement operations if you wish. LLMs will never have this level of control.
Lighting systems are an entire universe of reasons you should do it the hard way too. Being able to iterate light placement and intensity with nanometric precision starts out looking like a brick wall, but it turns into a superpower once your scene is halfway decent.
I can usually tell when someone used AI to do things like generate steam store art because their camera doesn't change in a physically plausible way between the horizontal and vertical layouts. When you have access to the raw scene you can place the same camera in multiple orientations without altering any other aspect of the scene. The header capsule and vertical capsule are very difficult to make look coherent if you are using an LLM to generate these assets. Your best bet with AI art is to render something so big that it can be cropped for both, which is also quite obvious and ugly. Being able to instrument a scene as if it were a real place is way more productive than an LLM once the scene is ~done.
A lot of people in the comments say that the supposedly better examples in the article are still “horrible” because they can tell they’re AI and point to things that the AI did “wrong” and a human artist would do better.
That may be true if you’re working with a top of the line artist, but in my experience the average freelance designer online is significantly worse than AI. I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models. Will a great human designer produce better output than an AI? Maybe, but a small local event or business probably won’t have the budget to hire them or know where to find them. It’s cheaper, faster and easier to use AI to generate something that’s good enough for their purposes.
People also point out all the little flaws in the “good” examples and cite them as obvious tells that they were AI generated. I think it would be interesting to see if people could reliably distinguish between AI generated flyers and human made flyers. Sure, sometimes it’s obvious like when the AI adds those weird, cartoony people. But if the model is told not to create designs like that and stick to the styles used in the second half of the article, I expect people would have a much harder time distinguishing the human designs from the AI designs.
I like this post. And the comments even more. I've rarely seen such a breath of opinions and analysis on HN. And it's all from a straightforward use case and a few examples. Is it HN tailored clickbaiting? If it is, it is the right kind.
Everyone's sick of seeing the same default ChatGPT style on posters for everything from village fetes to coffee shops to school plays.
But I'm convinced that just vetoing AI is to throw away the baby with the bathwater. So I set out to prove it.
Have you considered making the model leverage computer use via Work/Codex?
I'd imagine making the agents use the same tools that people utilize would greatly dial back how AI-generated these things look, and it would provide much better control too.
With Astra being genuinely much better at this, it should be more viable than ever.
every one of them still reeks of AI. especially the trend of icons next to the activities (tombola etc). its just a reskin but they all look AI, just not that triggering minimum effort AI look that is everywhere.
For some of them if you weren't told they're AI I doubt you'd be able to tell, as they look like normal graphic design posters I've seen pre 2022.
exactly. Hindsight is 20/20.
I believe the point is that there is no baby in this bathwater
What do we loose when we ditch generative AI? Easier poster making? What good does that do? So now pop&mom can have a poster in their shop that looks as if some graphic artist was paid for it, but wasn't. Will that drive the economy up? Improve poverty? Halt the war? Make life more tolerable? No, it just adds the pretense of having a professional designer, something that will quickly loose its added value when everybody does it.
That's true. Since ornamentation is effort-signaling, it may get dropped once it's cheap. Same thing that happened with clothing and home decor. The functional part may be beneficial though, even on utilitarian grounds. But yes, a lot of design is not about function but social signaling of taste and money as well as fashion.
This feels like an AI trap almost. A lot of the badness comes from people who don't want/can't put effort into it, so we all get a deluge of the sameyness.
Or is it? Could it be the well established low-effort tendency when the dominant culture is shopping centers, vehicles, similar eating establishments, and the style of suburban housing to a large extent? That would surely encourage the LLM to emit in a similar manner. That sameyness provides a signal of comfort and familiarity.
The author claims that the AI posters don’t have to be horrible, but fail to see that the dozen variations generated are not distinctive - they might have somewhat different typography or imaginary, but still have the same AI uniformity and smell as the crappy restaurant poster you see on the street. The core issue is not only technical, but also the lack of vision and imagination when creating art or even infographics.
The alternative is WordArt, or just black on white Comic Sans with some bolding and font size variations with bad ClipArt. These small scale events would never hire a professional.
I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
I see the chatgpt poster style on many small-scale local village events also. But again, what they replace wasn't any better. It's not replacing some beautiful craft that existed before.
I would argue otherwise.
whereas before I'd take a glance and go "hm interesting" or whatever, with these its just "oh look, it's AI slop" and that's all I will notice
I can't help but like the posters for the sheer reason that they annoy some annoying people who have a visceral reaction to the concept of AI.
why do you think this is the reason?
should I be cheering and clapping when someone goes on chatgpt and say "make me a poster" and they think they're a genius when this slop comes out?
You're just disgusted by the plebs and their taste.
what are you even trying to imply here?
should I be complimenting these default AI slop posters or be feeling good about them?
I never felt this way towards low effort / simple posters before, I thought they were fine
You just dislike their taste and the fact that they don't subscribe to your political crusade.
God forbid some overworked volunteer make a poster in 30 seconds instead of taking a college course to please some huffy internet commentators with an axe to grind
In the examples above, that’s really your own loss? There will only be one or two events in your local village, it seems self defeating to ignore what they offer because you don’t like the medium. At least these posters are well laid out and easy to read.
I am somewhat tired of all the AI posters, but I have to agree with what you are saying. The alternative was not any better. I think there's a persistent and very vocal segment of the population that just want to complain about anything to do with AI with a take no hostage approach. Some instances are understandable but if a local small town event or a low budget restaurant using AI to make a poster draws so much ire, I feel that it may be likely misplaced personal frustrations projected towards others. The response don't seem to be proportional to the offence.
We basically had two kinds of posters:
The later were awful, in the sense that I would never display them in my home as a reminder of a an event I took part in.
But still, they were nice because you knew someone took the time to create them to promote an event and share the important information about it, and each person was producing their own awful posters.
Now with gen AI we have something filled with trash, everything looks the same, the important information is hard to find...
Sure, the variations offered in the article are a bit better and more opinionated, but they still reek AI conformity and I feel sick looking at them.
I bet you would not feel sick if you didn't know ahead of time they were AI-generated. Some really are quite good.
You can't be serious... Are we looking at the same posters?
Yes. That's the issue: we are looking at the same posters.
It's just that "seeing this poster for the first time, unaware of the workings behind it" is a very different experience from "seeing this poster after you already saw dozens of other AI generated posters that used a similar style and had similar issues, got canny at spotting both the style and the issues in it, and came to associate them with cheap low quality work".
The former impression is "wow that's a good poster". The latter impression is "ew, it's posterslop". The poster, in the meanwhile, remains the same.
AI can often win in art contests - images, short stories, design. But that requires either sharp prompting, or an audience that's not familiar with "AI cliches". The quality is, if removed from the context, fairly good. If embedded in context, it's utter slop. The work is the same. Funny how that works.
The activities being perfectly aligned and normalized is the big tell here to me
Idk how to express it exactly, but I don't see how a human would have come to something like this
If you think about whether it is AI, are good at recognising those tells, an thinking about whether it is AI, then its probable you will spot things like that.
Most people are not that good at spotting those tells, and when looking at a poster they will not be thinking about whether its is AI or not. If its not obviously AI they are not going to even think about it.
At least in this case I can't pretend I have some kind of super power since I knew beforehand that it was gen AI.
And also it's not like I'm saying I love all the man-made posters. Or that I never been "fooled" by gen AI content.
It's just that as soon as I start seeing some gen AI tells on an image, I can't unsee them and I feel disgusted by it.
If there's nothing to think about they may well not think.
That's the problem.
Like how if you bought a box of chocolates, and it was actually filled with rocks, you wouldn't dislike it until you found out.
Immediate glamor followed by gradual disappointment is AI output all over.
It's saturation.
If I saw an Images 2.0 flyer in year 2020? In a world where Images 2.0 didn't exist? I'd be impressed. But if I see it now, today? I'm not impressed at all.
It's the same image, produced by the same AI and seen by the same person. So, what's the difference? What changed over time?
Saturation. "I've seen it all before." AI made that specific flyer style plentiful and omnipresent, and that made it "derivative" and "cheap". What used to invoke "cool" and "wow" was turned into a dreary cliche by repetition. Flaws that were easy to overlook when overshadowed by novelty stand out like a sore thumb now that you've seen them before in the same patterns many times over.
The image is the same - it has the same strengths and the same flaws. But your focus is shifted by familiarity.
It's the same mechanism that drives trends and fashion. AI just supercharges it.
Naturally, you can avoid a lot of it by using careful prompting and steering to guide an AI away from the "cliche" style-space. You can get something with both good quality and good identity that way.
But that requires: being aware of the problem, being really good at prompting, and putting in a considerable effort. It's hard to steer a model away from "AI cliches" if you don't have the eye to spot them in the first place.
Most AI-generated content doesn't have that kind of skill and effort applied to it - it simply uses the "model defaults", and gets the "model defaults". For all the good and bad that comes with those.
Some level of uniformity is fine and indeed the norm. It was uniform back when posters were hand painted, eg 19th century world fairs or zoo openings or theater posters. They look pretty similar. Carneval posters looked similar.
The expectation of some kaleidoscope of styles is not really grounded in how things used to be ever.
Also, it's just nostalgia, just like how some young people now think audio cassettes and discmans are "cool" and have some revival, some are nostalgic for the back-in-the-day Word posters because "at least back then", but "these days" it's decline etc. Pretty sure in a few years people will be nostalgic for crappy AI slop of 2025-26 because their shittiness will feel like some charm compared to whatever the AI will be able to do.
I'm not sure about that. I, myself, am not skilled enough to make a nice poster, so when I needed one, I used to asked my skilled friends to do them for me.
But sometimes I also purposefully made myself some Comic Sans stuff, exaggerating them in every possible way, as a joke. And it was well received because people knew it was my own work and understood the joke.
If I made this today, it would not be seen the same. People would thought I'm trying to fight gen AI trash or I'm nostalgic of the past. While I'm just trying to make a joke by making something awful on purpose.
And I couldn't do the same joke using gen AI. The "on purpose" cannot be conveyed. People would just see gen AI trash.
Making stuff that's bad on purpose is annoying, like acting retarded ironically. Make good stuff or just spend little effort. Putting in effort to look low effort is just trying to be special when you're not.
I was one of those "skilled friends" that people go to, to make those posters in times of need back in school. And this was many years ago. Didn't enjoy it, but just did it as part of volunteering, or help the student community or a school club out.
Some people enjoy doing that work, but most people did not, and I was often the last resort because a random club or activity could not find suitable help in time. So had to step up when a friend or acquaintance asked.
I think there is some misguided view where in "the good old days" people designed everything by hand. From the perspective of someone who had to make 10-20 of those a year as a volunteer, I can say it came at personal cost, often caused distractions from the actual event, and there was not enough people who stepped up to get it done. If it was so enjoyable we would have no problems finding people doing the work and that was not the case.
The posters and designs were often rushed out late night by the closest person you can find who had a copy of photoshop on their computer. If we had AI back then, I would bet you 100% it would be the preferable solution and no one would bat an eye. It wasn't the type of work a lot of people wanted to do, could do properly and is willing to do for free, at their spare time, rushed for a deadline.
Sorry, but Walkmans and Discmans were considered cool... At the time.
Personally I like simple designs. I always remind people who make posters that whoever looks at them will only do so for a matter of seconds. If you want extensive detail, put it in smaller print. Put the main hook in large letters and a brief description.
But they became uncool when the iPod and mp3 players came out. Nobody felt sentimental about VHS artifacts either, and now it's a genz aesthetic or something. These things cycle, like I'm sure some old folks miss the radio hiss and listening to football matches with just audio.
If you read the article at all, the "everything looks the same" is easily fixed with just a tiny bit of effort.
It's not AI causing the sameyness and hard-to-read nature of these posters, it's people being lazy. I personally think there's a few nice looking ones in there (the punk fanzine style for one).
Sure it's not some 9/10 hand made poster, but considering these take 30 seconds to make, it's impressive.
??
The alternative is people just taking some markers & a sheet of paper, or chalk and a blackboard.
If you travel around east Asia you’ll be delighted by the variety and creativity of these handmade signs. Way better than anything produced digitally.
But of course their relationship to handwriting is completely different there compared to the west.
The variations the author generates are night and day better than the "piss filter" era slop in the first batch.
Some of them would have passed as intentionally crafted by a graphics designer before AI.
And let's not forget that before AI, many of these would be word doc printouts with clip art. The alternative wasn't hiring a designer - the alternative was doing nothing special at all.
I was honestly ok with the silly looking posters. Where I'm from in italy it's common to have sagre, sort of cheap food events sponsored by the municipality/local shops. Before ai the posters looked like each other (as in, poster typically looking like sagre posters). Now not even that, they're just slop ai that could be everything before you read. Nobody needed better looking posters in this case...
Before ai example https://www.sagretoscane.com/sagre/fi/rignano-sullarno/sagra...
Post Ai example https://www.instagram.com/p/DZiKFZgIwcY/
Here's an article by the biggest online Italian newspaper, worth reading translated https://www.ilpost.it/2026/07/26/ai-locandine-sagre/
For me what always gives it away is not the posters themselves, it’s the context. These are all overdesigned for a local community fair. There is no way they’d be paying for a professional designer for this, therefore it’s AI.
On the other hand if it had word art, grammar/spelling mistakes, images with wrong aspect ratios or clipping issues, that would immediately convince me it wasn’t AI.
Prompt: make me a poster in the "looks like garbage made by someone who doesn't know how to use Microsoft word or what aspect ratio is" style...
Context is everything.
A twee handwritten sign for free range eggs at the roadside is likely to do well.
A handwritten sign for flying lessons on the other hand..
Hard disagree: every single example TFA gives is way better than the horrible generic ones that are polluting every shop and LinkedIn post.
It's not even close.
That's not what OP is complaining about. The issue with AI art isn't how the individual piece look, but the similarities they have in aggregate. One image can look perfectly fine, once you seen a hundred they all start looking extremely similar. Human brains are great pattern recognizer and lock on to those similarities, even when they are covered under different styles.
When all your art comes from a single source, it's difficult to create real diversity and novelty. That's still the big issue when it comes to genAI in general, without a lot of hand holding you'll just bound to end up with slop, since the AI won't get creative on its own.
I am not sure. If something is not in the usual AI style its not going to leap out at you that it is AI the same way. Maybe if thought about it, but when someone looks at a poster they typically focus on the information, not the style.
Did you look at the examples? They're almost ridiculously diverse, and the prompts show very little handholding was required.
They're not novel, but a poster for a spring fair isn't supposed to look like a de Kooning.
These arguments are almost completely detached from reality. Most artists aren't diverse either - they're told to find a style and stick to it, and that's what they do.
Commercial graphic designers are more versatile, but the set of standard looks is still relatively small. Hollywood movie posters and book cover designers are notorious for reusing the same tropes and colour systems, and that's been true for years, long before AI was a thing.
You have really try hard to see that. It is good enough to not give immediate annoyed reflex of seeing something in the same ubiquitous default chatgpt style.
For goodness sake - these are just a fair posters.
They look absolutly well done.
Idk, those are more than alright to my eye. Surely they won't win any design awards, but as a throwaway poster for one time event these are miles better than any amateur work.
It doesn't fail, it actually demonstrates how the model can improve the output if the prompt is better. AI generated websites look like crap because developers don't know any design language so they have no idea how to prompt the models to get something good and more unique and creative out of them. This shows that you can actually achieve that with just slightly better prompting. Just like with programming, actually.
Designers republic and memphis were the only designs i couldn't immediately see were AI generated.
The only reason i couldn't tell memphis is because it's aping a known design language already, it's just a perfect copy so me not being able to tell it wasn't AI isn't a free pass in this case.
I think if there was a little less "grid" feeling to the layout details then i wouldn't be able to tell on a few of the other designs either.
Edit: the designers republic version is quite a lot different than the others, it's not just that it's the only design to avoid pairing every feature with an icon, it's the whole layout variety - there's different font sizes, the positioning of elements is very well done to my eye. I'm gonna say this has to be another case like memphis, there's some pre-existing design language that i don't know of and it's just aping that. It's much more human than the others which i can believe are straight ai.
But the thing is, all have that icon+text style in the "tombola, cakes and drinks..." part. If I wanted to be distinctive, this is what I would have tried to get rid of at first, not the "visual style" (it's sort of like Windows XP visual styles, no matter how different they are the overall layout is still recognisably Windows).
yeah
although I guess it's that the author used the same context with the original generated image and thus it just reused that icon+text thing
but in general, these models do seem to be kind of just go for an information-dump type of style where its just listing everything and putting as much stuff in that is associated with the words, which is what these LLMs do
so you'd probably need to steer them heavily with explicit instructions on what to do and how to get rid of it, which I'd bet nobody will actually do when making these posters
It’s not complicated - the default style signals low effort. Why should I get excited about the village fete if the organizers put in the barest minimum of effort?
But there’s another reason it drives people crazy - it’s low effort trying to present as high effort. If the sign was simple Comic Sans then it would at least be charmingly honest.
Because there's no correlation between the ability to organise a village event and the graphic design skills. (Apart from "it's been so successful we can splash money on a design agency") Maybe someone actually liked it and thought it's enough. I've seen groups overthinking posters and it felt similar to groups at uni overthinking funny names instead of doing the work that actually mattered.
To be clear, I'm not saying those designs are good, just that most of the time the design is not the point and minimum effort above "Times New Roman 12pt" is what many people always wanted to do.
Which could be an important signal for you to decide if that's the kind of event you want to go to. Maybe the comic sans fayre is preferrable to some.
Graphic design skills don’t correlate with effort. I’ve seen terribly designed posters that the makers clearly put a lot of effort and love into because they loved whatever it was they were promoting.
I’ve also seen people put a lot of effort and love into poster and stuff because that interests them (doesn’t mean they’re good at it either), then the event is utter crap because they didn’t spend much time on the actual event.
The last paragraph in GP’s comment is the key. Nobody would care about a low effort poster, what they care about is the deception of pretending you put a lot of effort into the poster. It’s dishonest, and it would make me subconsciously question what else they’re being dishonest about.
I think this (low effort posters) rather signals to me that they have the right priorities. A true professional poster would tell me that it's some commercial cash grab instead of real local enthusiasts making something normal.
I am inclined to agree. Small community organisation cannot afford to pay a professional designer. They might be lucky and have a talented volunteer, but in general its a waste of limit resources.
You don't have to get excited by anything. You are welcome to boycott the village fête because you think they didn't put enough effort into their poster. Your choice, my friend.
Personally, I’d prefer people who get upset about “ai slop” to just stay home and complain about the fliers. It’s a great filter.
Making a good poster is bikeshedding. Organizing an event is hard and making better posters than this is a waste of their limited resources.
Ok, don’t go because of the poster. Miss out.
I live in a village with lots of local events and I do not care about the design of the posters. I just care about what the event. I just want some information.
No one cared about shitty posters before (and yes they are shitty) and no one cares about them now.
No one is praising or collecting them. We just accepted that shitty poster exist.
Now some few people complain about ai slop at situations were no one cares and no one cared /shrug
That icon+text row is the tell for me too, though I'd blame the prompt more than the model, nobody ever asks for an awkward layout.
That default style is very recognizable. I am seeing it everywhere.
I guess it is like the early days of wordprocessing, where you saw Comic Sans everywhere.
The early days of word processing that I remember involved monospaced serif fonts, with lines exactly 80 characters wide.
But if a designer improves an AI design and I feel it's fine, does that make me strange? If you ran a blind test on this, I think it would come out with high preference...
I think this is a misdiagnosis of the problem. The AI posters are just fine, perhaps even pretty good.
The problem is that using AI to create the posters show a lack of willingness to put in effort, and it makes you question whether the producer cares about the product and whether they care about the large scale societal problems related to the usage of post-2022 transformer based neural networks.
How much effort was put into these things pre-AI? None of these are big professional things, just local events. Those never had professional posters.
Or they would pay a designer to do it for them. Also no effort but just cost more.
Do you only buy hand-churned butter?
Most fliers put together for community events pre-AI were Microsoft Word or Google Docs plus clip art.
The world is getting better, but before everyone realizes it we have to complain first and reminisce about the good old days of Wingdings and Comic Sans.
It’s actually very amusing to me comic sans is being referred to as “charmingly honest” on this forum, of all places. Shows how much this is all just aesthetic judgement and doesn’t have any connection to reality, just opinions. Before, comic sans was so low effort it earned scorn and derision. Now, it’s charming. Meanwhile, it’s actually the same amount of (low) effort as always. But for some reason now it has been elevated. Seen people say the same about MS paint drawings, and that’s when realized this isn’t serious at all.
Everyone is suffering and not getting what they want to some degree. Life is short, and opportunity runs out. People turn this into bitterness and direct it at external things that are going well that they're not a participant in.
It's not just AI, it's everything. Romantic rivals, celebrities, sports teams, fandoms, choice of IDE or programming language.
It's a social evolutionary strategy to neg and gossip about people and things you don't like or are jealous of. It's low energy, has little downside, and can reduce the fitness of rivals, especially when done in group settings.
The algorithm has co-opted this part of our primate brain and turned it into ad dollars.
What's interesting is that you can't do the same with long-form AI prose. You can ask any given LLM to write in different styles, but it will always fall back on the same rhetorical and structural techniques, so the "new style" is strictly surface-level. In fact, it's getting worse over time -- especially in Claude from Opus 4.6 --> Opus 5.
I suspect that the same thing is happening here -- as other comments note: lack of distinctiveness, uniformity -- but that the low information content of posters prevents it from becoming immediately obvious.
It's a thing inherent to diffusion models I think, a kind of uniformity of content across the image.
The similarity may be partly the image model's fault – especially if it's been post-trained/distilled towards performance, correctness and "quality" (for some value of "quality" anyway) which inevitably occurs at the expense of creativity and variation.
But I think it might be more about the LLM's lack of creativity in coming up with the prompt for the image (or "embellishing" a user's prompt), or directly the embedding vector if the LLM is itself the image model's text encoder. Then whatever the image gen outputs is simply an instance of the GIGO principle. It would be interesting to test whether similar cliches and motifs also occur if you ask the model to create an SVG rather than a raster image.
AI posters may or may not have to be horrible, but they absolutely must include [ icon | icon | icon | icon ], apparently
The Designers Republic one arguably avoids it. Only one of its five is an icon: three are zero-padded numbers and one is a smudge where someone forgot to stamp the icon.
I see, across my city and others I visit, every bar/restaurant/etc now has low effort one shot posters, menus, etc, some with old chatgpt nonsense text / errors. It's everywhere. All that brown-ish hue food 'pictures' etc. I mean 'authentic Pizza napolitana!' and then an AI generated picture of said pizza... One of them (an Italy born Italian restaurant owner here) and he just said; people come in with the very expensive pictures / menus I had before and the same amount of people come in with these free ones. And he actually likes these better as photographing (real, not mcd/burgerking plastic props with poison paint to make it look better) food is hard, even when paid for.
I'd rather not see photographs in the menu then seeing fake images.
Here in Bielsko Biala (southern Poland) I see the same in few pubs, never seen on menus though. Shops seem to be creating lots of marketing images as well with AI and it just looks...off. In any case doesn't make me want to enter the place.
AI posters are not horrible, they just expose the person who "commissioned" them as trash. In a way, that is a good thing, since you can avoid them more easily.
The only thing that separates you from trash is that you meticulously hand-craft your posters.
Their very first attempt is arguably the best one there. I was surprised they didn't like it much and kept going. Then the "Stamp / Letterpress Style (Modernised)" was the only other good one.
So of the two designs made, only two were good, the rest was quite bad and lost all meaning.
Moral of the story - have taste.
Just like in engineering.
these are definitely better.
I really wonder what's going on in the minds of those who make the shitty AI posters? like, are they that unaware?
for me when I see them I just get instantly repulsed
It's pretty sad when you realize the average person is just kind of... unaware. They are fine with whatever, they don't really notice most stuff that goes around them.
Most AI-generated art is "good enough" for most one-shot designs by now (though still not [always] as good as a good meat-based artist of course)
The problems right now are:
- Maintaining a consistent and coherent style/aesthetic when you have to generate lots of assets for something. For example sprites in a video game.
- Iterating over a design for more than a few passes. For some reason most models keep degrading the entire image if you keep asking for edits to a specific part of the image. Or, some problems are or become impossible for them to fix no matter how you prompt them.
I remember seeing that default style long before AI. Probably where it came from. At least the default is not Corporate Memphis.
It's not that the first one is so awful in isolation, it's that they are everywhere you look when you walk down the street. The barbers, the school fête, the cafe, the church. Everywhere.
As usual, AI is a tool and will be good in the hands of the wielder. I've been saying this since Stable Diffusion released nearly half a decade ago.
I like the other posters more, but the first poster probably still conveys the idea of the event better: people having fun, drinking beer, with a live band. You don't get that from most of the other posters unless you first mentally transform those icons into real things, which takes effort.
People dont want to write multiple prompts or write a lengthy one. They want to say create poster x for event y. That's it, that's what they get and that's what they take.
Kids are rediscovering typography and pictograms. With AI. Well done!
Buried at the end of the article the author linked a library of different art styles applied to the same poster content. Found some new cool art styles to try out in the future. https://john.hartnup.uk/poster-prompts/
No, they aren't.
AI is a tool, just like photoshop was. Just because someone bought photoshop didn't mean that they can magically create amazing digital artwork, they had to learn photoshop and also be creative. Otherwise it would have been a horrible poster with comic sans. Same goes for AI, one has to learn to use the tool and be creative.
They are not OK.
I love how the AI silently injected "A day of fun for all the family" on the hand-drawn by a child design.
PS: Which then survives in the next iterations as "A day of music, making and family fun"
Edit: Ah just saw the call out on the previous iteration.
But still it's a nice display about the semantics encoded in the models.
Can you tell your AI to not apply piss filter to everything?
One of the biggest problems is actually making sure the information needed is on the poster.
Times, dates, location, pricing, parking etc…
As he points out “it added a bunch of text…” now it’s one all the future designs. That’s great - is the text correct?
To be honest this was a problem before AI. People are not very good at communicating.
I think we're in the 'early digital camera' phase of AI art gen.
The real photographers knew they were shit photos. They were grainy, bad lenses, and ugly. A lot of people still liked them because they were much more convenient for a lot of uses than the film ones.
Well, I guess there's still a lot of film people. But film had a ceiling. Digital cameras kept getting better.
The adaptive film photographers eventually adopted the tool. A lot of their skills transferred well to the new medium. Most waited until the cameras got good enough, though.
I'm not sure when that'll be with AI art gen. Seeing scenes broken up into layers in the latest gpt image generation, though, made me think we might be near.
Incidentally, the "early digital camera" aesthetic has been back in style for a couple of years now.
At least the AI generated posters are better than human-generated t-shirt designs, where you find generic texts such as: "Est. 1984" (or any random year), "I [heart] NY", "Property of [City/School] Athletic Dept.", "Original Trademark", "Authentic Denim Brand", etc., etc.
All trash, in my opinion. Different flavors of trash.
At a certain point, pottery that looked like a child made it became the high end, because well-executed pottery was coming out of machines.
We've officially reached that point with advertisements. Save your tokens. Hire your 9-year-old niece to draw the poster by hand and you'll likely get a far better reaction from most people. Nobody goes to a fair because the poster had a "modernist / Bauhaus-influenced graphic style".
if NOT TRULY personal preference, then all those variations ARE horrible, but if they serve some taste--personal or marketing--then they are likely not to everyone's taste.
to me, they all look like lazy-prompting, which is the only way I ever do genAI imaging, because I fail to see why that "CPU" should be wasted on something I barely even care for.
That said ... let kids do that shit and pay them 50 or 100 bucks ...
The issue is that in my walled garden, I have not seen any of the good AI stuff. My wardens still use some home trained GPT 3.5 for most stuff, including their songs on potify and bootube. And i can't get access to current top level public AIs, either. Had the actual ChatGPT and Claude models for some while but I knew why ... otherwise I might put effort into semantics, syntax, grammar and my image generation prompts, which currently look like some MITM is speedrunning collages using haiku cowork and crayons or something ...
If only there was a way to precisely control our output so it matches our taste and imagination. Some might call this technology, drawing.
I find it kinda funny that even "smartest", most capable models often have a very hard time going beyond surface-level, top-of-mind associations, when faced with creative tasks.
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.
If you understand how curve fitting works, then it is a very predictable outcome.
Sure, but what's interesting is if you tell it to "behave unpredictably" or "don't use tropes" it usually fails down the same curve. Which is predictable, but telling.
I remember seeing a poster for Chinese New Year years ago, and someone had included the kanji for Japan on it (日本). Obviously they just wanted generic looking characters without bothering to see what they meant. I couldn't resist writing a comment on the poster about it.
It showed whoever did it had no clue about East Asia or Chinese script...
Considering your prompt fits exactly that description I think the AI delivered perfectly. Try using some actual design language and see how well it does.
Isn’t the most overused trope the most statistically weighted to be chosen from a group of options? It makes technical sense but as you say leads to boring outcomes
The masses love clichés and stereotypes, which is why these "artiste" designers frequently miss their target audience.
Is there a way to formalize the space of all possible aesthetics a model knows, in a way that you could randomly sample from it?
The analogy in my mind when I read this post was: you are asking a machine to paint a color, but the machine always paints the exact same shade, deterministically; and you'd like to explore different colors, but somehow you don't know anything about colors, don't know any of their names. So you don't have the language to ask for what you can't name.
Random sampling of colors (without names!) is a solved problem, because we've parameterized the entire universe of colors that can be perceived. It's just a very low dimension manifold, and there's even a computable metric on it such that unit-distances in that metric are what humans say are color differences of equal step size.
Are there more general versions of this? Like: "Here's a list of every human art in history: infer a coordinate system that uniformly metricizes every art that can ever exist?"
Adding a safety pin to the punk design was too much of a cliché.
I wasn't a fan of the Memphis one as it reminds me of the worst eighties and nineties designs.
Well, sometimes AI generates pictures that are not bad. Personally though I am tired of AI slop in general, and I don't want to support it. AI literally kills humans. In some scenarios AI is still useful (e. g. if you write a game, say, in javascript and you don't have any designers helping you out, you could generate images that don't suck, quickly, via AI) but other than that the less I get of AI the better. Google now has that problem with AI - tons of AI slop and fake videos. I realised the AI slop just wastes my time but Google does not offer a simple "do not show me any AI slop" videos. After all they want people to waste their time on youtube, by design. So I now waste my time twice by using Youtube, if I watch an AI slop video.
This isn’t a web UI, it doesn’t need icons.
But more importantly, if you aren’t the kind of person who could make a halfway decent text only poster before, you are going to make the posters at the top of the article. Those are objectively harder to read than something typed up in word.
You aren’t going to know to tell the AI to “ Go for a clean, unfussy, bright layout with a bold striking spring-themed graphic. Avoid pastel/airbrush/oil style art or images of people.”
The only ones that aren't horrible manage that because they're so bland there's nothing to go wrong. Look at an example with some detail, the "Now please make one in the style of a 90s drum n bass gig flyer, with early 3D/fractal computer imagery" poster.
At the top of the page we have a deformed wireframe sphere. A wireframe sphere is stylistically appropriate, but the incorrect rendering is not. The "CGI" aesthetic requires obviously computer generated lines, which in the 90s meant accurate and regular lines.
Next we have a messed-up stellated polyhedron, and a messed-up dot pattern. These also fail for the same reason. The main 3D rendering is also obviously broken, as are many other small details.
But the biggest failure is the complete misunderstanding of the culture. 90s DnB was absolutely not about "good vibes". The smiley face logo is completely inappropriate; that's associated with late 80s/early 90s rave culture, pre-DnB era. 90s DnB was much darker and edgier in tone. The scene was almost exclusively male, and it maintained a aggressive vibe carried over from jungle.
A 90s DnB event would never advertise "bringing communities together". Audiences would be repelled by such messaging. This is despite it actually doing just that, as the scene was racially integrated in a way that mainstream music at the time was not. If there's going to be pro-social messaging on the poster it has to be there only implicitly.
I'm reminded of how Mac apps are supposed to conform to common UI standards rather than going off and reinventing the wheel. Also the Bootstrap template for websites.
Similarly, it would be nice if there were common styles for posters that you could just use and an AI could generate and nobody would criticize you for. Not everything has to be an original design.
Only the last poster kind of gave me vibes, the other ones are absolutely soulless and slop.
I guess it works for the target audience.
Yeah, and adding an explicit "no sakura, no rising sun" list does half the work.
Generative AI is actually pretty good at giving you rough concept sketches and iterating on top of existing renders.
However, you must retain control over the scene graph and its composition. Use the output of the AI to guide how you work it. Do not assume the AI system has the ability to simulate world space with any meaningful fidelity. You can move transforms around in Blender and Unity with floating point bit increment/decrement operations if you wish. LLMs will never have this level of control.
Lighting systems are an entire universe of reasons you should do it the hard way too. Being able to iterate light placement and intensity with nanometric precision starts out looking like a brick wall, but it turns into a superpower once your scene is halfway decent.
I can usually tell when someone used AI to do things like generate steam store art because their camera doesn't change in a physically plausible way between the horizontal and vertical layouts. When you have access to the raw scene you can place the same camera in multiple orientations without altering any other aspect of the scene. The header capsule and vertical capsule are very difficult to make look coherent if you are using an LLM to generate these assets. Your best bet with AI art is to render something so big that it can be cropped for both, which is also quite obvious and ugly. Being able to instrument a scene as if it were a real place is way more productive than an LLM once the scene is ~done.
A lot of people in the comments say that the supposedly better examples in the article are still “horrible” because they can tell they’re AI and point to things that the AI did “wrong” and a human artist would do better.
That may be true if you’re working with a top of the line artist, but in my experience the average freelance designer online is significantly worse than AI. I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models. Will a great human designer produce better output than an AI? Maybe, but a small local event or business probably won’t have the budget to hire them or know where to find them. It’s cheaper, faster and easier to use AI to generate something that’s good enough for their purposes.
People also point out all the little flaws in the “good” examples and cite them as obvious tells that they were AI generated. I think it would be interesting to see if people could reliably distinguish between AI generated flyers and human made flyers. Sure, sometimes it’s obvious like when the AI adds those weird, cartoony people. But if the model is told not to create designs like that and stick to the styles used in the second half of the article, I expect people would have a much harder time distinguishing the human designs from the AI designs.
AI posters are like using the Papyrus font.
I like this post. And the comments even more. I've rarely seen such a breath of opinions and analysis on HN. And it's all from a straightforward use case and a few examples. Is it HN tailored clickbaiting? If it is, it is the right kind.