alt Hacker NewsAI-generated posters don’t have to be horrible
Comments
Nothing in that article isn’t horrible to my eyes.
From a creative direction perspective, I think this is missing a major part of the story and what's driving much of the slopsign aesthetic.
Your prompts and turns help with the graphic design portion of a poster. But, if you're a restaurant owner, you're doing both the graphic design and the food photography in GenAI, which further compounds the signals of slop that can seem unsettling to someone viewing it.
The former is much more tunable than the latter, but the end diagnosis remains: if you can't tell what's bad in a design, you won't be able to tell what's good, and no amount of turns will iterate towards it. This is one layer above your scope. Art direction encompasses both, because there's a relationship between media and graphic design, especially when you have products to show.
Remember back in the day when people used to insult human-made art by saying it was "derivative"? Yeah, this isn't an AI era phenomenon. I think some of these posters are good.
Some of these are actually... pretty good. I used to do print design to pay my way through college, and they wouldn't be too far from run-of-the-mill pamphlets we would turn around (both design and print in small runs) over lunch.
Well, they're superficially less same-y, but none of them are really giving spring fair vibes.
Except for the "professional graphic designer has added typography to a poster paint drawing by his young child" one, I'd go as far to say that I actually like it, especially if you were to remake it with the assistance of an actual child.
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.
Pay. An. Artist.
These models are built on IP theft from artists who are now losing work to this slop. Even if you don't see the difference (rest assured, most of your audience will), the morality of it is terrible.
Indeed, the most important function of a designer, tailor, decorator etc. is filling the weaknesses in the client's request with actually good taste.
The icon list in every poster, no matter which style (even the minimalists) is what's killing me.
> Inspired by this blog post, I went on to make a catalogue of one hundred poster styles, with ready-to-paste prompts and example images for each one.
This is really cool! I don’t ever make posters - but I can imagine these being super useful
Sure, you can get any style you like, but /you will pull those little icons lining the list of activities at your county fair from my cold robotic hands/
I've been trying to help someone create publicity images (who can't afford to pay a designer). The biggest problem with AI is modification of input photos. The results are good, but still trying to get it to not "sloppify" the images.
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.
Would be interesting to see if it could use CSS Zen Garden to build the posters.
The point really isn't just the use of technology. People don't complain when a hand drawn poster is photocopied! The issue is that it's taken a human out of the creative process _and_ it's using the plagiarism machine that is also making everything worse while enriching a handful of the worst people. It's a sign of how lazy the event organizer is, and how little they care about people, which is especially foolish for an event where you would like "people" to show up.
That first poster example is exactly how every poster at my kids school looks. If theres ever any carton people they have extra fingers or are reading books backwards.
Prompting is an art
I did not expect to see a Leamington Spa beer fest poster being used as a reference image today.
Early dnb gig flyer gave me rave days nostalgia
They may not have to be horrible, but they DO have to be beige... apparently?
Why do the ChatGPT posters always have a lot of dividers? No matter how you change the style, it's always there.
It all reminds me of when Amazon website used to get laughed at but those who overweighted their design preferences. The first ai poster in the list look fine to me
Good "taste" and knowing what you want (and don't want), seem to once again be the trick to success with LLMs.
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?"
For anyone here who works at Anthropic or OpenAI, this is the doing of your lovely CEOs and their constant fear-mongering that has turned an entire population of people against anything even remotely touching AI.
Community flyers have been notoriously cringe for a very long time. In the 1990s they were all Comic Sans with cringe Microsoft Word clipart. Then, the design world decided that Comic Sans was the bar for bad taste.
Even if these examples look lazy, someone still had to do the work to prompt the thing into existence and they, at the very least, found it acceptable. So, either way, it had the same amount of effort it always had.
Man, I must be so basic when it comes to such designs. They all looked fine to me lol.
For your basic words-and-dates-with-shapes-and-shit posters, the AI ones are annoying, but I’m not gonna die on a hill over it. The hill I _will_ die on is restaurants using AI generated images of food. No. That needs to be illegal. I thought it _was_ illegal.
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.
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.
AI posters may or may not have to be horrible, but they absolutely must include [ icon | icon | icon | icon ], apparently
This article is doing the whole concept a disservice. It's still just randomly generating without thought; albeit maybe with a drop more taste than usual. (not a significant amount of taste, just a single drop).
The problem with a lot of AI is that the baseline is already past "good enough" for many folks.
But you can also imagine a very different approach:
Imagine if you start with a vision, and just happen to use AI tools as part of your process to realize that vision, just-like/along-with many other implements. I've seen examples where people put together many layers in photoshop or gimp, and mix with rendering, hand drawn art, photographs, etc. Very much like how some of the better programmers work with AI assist.
This is one of the most interesting posts I've seen, and that's the way people should work with AI. A brainstorming session, with background and references, with broad knowledge of the field, then with clear instructions on how to proceed, different designs, propositions out of the ordinary, etc
I've been doing that for the last six months and the results are more than spectacular for the apps I build
So no, 'create an inventory app' is not enough, you have to be specific in every sense, every detail of the tech stack, phases, checklists, roadmaps, decisions, everything that makes AI's life easier (less mistakes to make and fix) and yours too.
Next time, start with "Let's have a brainstorming session about an [inventory] app we will create and at the end write a very detailed prompt.md, here is the initial context... ask all the questions you may have before writing any code"
* Replace [inventory] with any other app you may need
And remember one thing, AI is a multiplier of both our intelligence and our stupidity, the outcome will reflect that
Edit: The link at the end deserves some exposure, it's the work of the author showcasing 100 prompts for different designs [1] and some people won't get there because tl;dr or short attention span. Get them, use them, learn from them
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.”
AI is killing designers, and this guy just delivered the final blow.
Thank you! These are so nice compared to the 1000 times repeated AI graphic I see everywhere.
It's almost like you'll get much better AI generated posters if you're experienced at graphic design and know exactly what you want to create given what the client that is paying you for might want.
Interesting...
(A lot of people end up using Canva for this kind of stuff, btw)
Yeah, and adding an explicit "no sakura, no rising sun" list does half the work.
It did pretty great on the 90s drum-and-bass party version at the end, takes me back! :)
You need AI for this?
Go to Pinterest, search "poster", find some cool ideas, steal it and do it in Inkscape in 30 minutes.
Has the world gone crazy?
Perhaps... but is this all you found once you made it into the Ministry of Information? Perhaps this was a sort of Information Retrieval all its own?
Ironically the author isn't immune from publishing slop themselves. https://john.hartnup.uk/backpressure/
Like HDR photos of the mid-2000s, these too shall pass.
It's interesting how the negative examples all look like mobile game ads.
Which isn't an accident - mobile game ads are tuned studiously on consumers actual preferences and not the preferences of designers. i.e. the people that are likely to spend actual money on the product/service being advertised to prefer the ad being portrayed here as bad.
Bluntly, being able to sidestep the whims and fashions of graphic designers is proving to be a major feature of the AI revolution.
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.
It is kind of sad that whenever you see art now, whether it's good or "bad", it's uncertain if the artist actually made it, or just prompted AI.
The second options seem very similar to the popular templates in canvas.
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.
I don't often say this but those jobs are ripe for replacement by AI. It won't do worse!