[HN Gopher] Coarse Is Better
___________________________________________________________________
Coarse Is Better
Author : _dain_
Score : 169 points
Date : 2025-12-21 12:57 UTC (10 hours ago)
(HTM) web link (borretti.me)
(TXT) w3m dump (borretti.me)
| airza wrote:
| Years of refinement on the taste of people with no taste has
| produced a model with no taste. Crazy
| drob518 wrote:
| I tasted the model, but then I spit it right back out.
| mcpeepants wrote:
| they put a special coating on the model to discourage this
| behavior
| drob518 wrote:
| Ah, that explains it.
| Undertow_ wrote:
| it's not shocking that this is the result of "art" from people
| that think complexity and accuracy are the only qualifying
| factors.
| spaceman_2020 wrote:
| While I don't disagree with the author, these are simply two
| completely different tools with different use cases. Nano Banana
| Pro throws out fantastic images you can actually use in your
| marketing right away. It's not an art tool - it's a business tool
|
| As long as the older tools still exist to make art, I don't see
| what the problem is. Use NBP to make your marketing pics, MJv2
| for your art
| Zak wrote:
| The author claims the old models are better at creating art than
| the new ones. I disagree; art requires consciousness and intent
| while this type of model is capable of neither.
| LatencyKills wrote:
| I define art as something that evokes an emotion or feeling.
| I've seen people wax poetic about the "meaning" of an imagine
| only to find out that the image was created synthetically.
|
| Were those "feelings" not authentic?
| neonnoodle wrote:
| If I see a cloud in the shape of my childhood dog and start
| to cry, is the cloud art?
| rtldg wrote:
| Yes. The Earth and its formations are art. I disagree that
| art requires consciousness and intent, but those admittedly
| do improve its value [to me]. (For reference, I value AI
| content/art poorly and avoid it)
| only-one1701 wrote:
| Everything is art, fantastic. I see nothing wrong with
| this definition.
| card_zero wrote:
| We have at least established that very boring pieces,
| such as Andy Warhol's _Empire,_ Kazimir Malevich 's
| _White on White,_ and John Cage 's _As Slow As Possible,_
| are not art.
| only-one1701 wrote:
| Bad code is still code. A painting of code is not code.
| card_zero wrote:
| I think you're saying bad art is still art, but I'm
| unsure what to do with the second sentence. I'm toying
| with "an encoding of art is not art", which might mean
| that art has to be available to an audience.
| only-one1701 wrote:
| Is a car crash art?
| RHSeeger wrote:
| A drawing/painting of a car crash certainly can be
|
| https://www.etsy.com/listing/4329570102/crash-impact-car-
| can...
|
| As can a photo of one (sorry, I don't have a good example
| of that).
|
| And, both a camera and AI are an example of "using a tool
| to create an image of something". Both involve a creator to
| determine what picture is created; but the tool is
| central/crucial to the creation.
| card_zero wrote:
| When I was about 12 a car crashed in my quiet street
| (somebody tried to drive it through a concrete fence), so
| the next day I sat in the street and did an ink drawing
| of the wreckage with a mapping pen nib. That was
| excellent art. Then I stole one of the gigantic
| suspension springs and took it home to use as a stool,
| which by some silly definitions was also an act of art.
| But this all evades the original question about whether
| the actual car crash is art for evoking feelings, or
| whether art in fact must involve pictures, or human
| communication, or what. It's one of the impossible
| definitions, along with "intelligence" and "freedom". I'm
| a fan of "I know it when I see it".
| only-one1701 wrote:
| I would never argue that a painting of a car crash
| couldn't be art. It's funny your bringing up that a
| camera is a tool for creating art; I also hold
| photographic art in lower esteem than other kinds of
| visual art (though I still think some kind of photography
| can be art).
|
| At a certain point, we need to be realistic about the
| amount of effort involved in artistic creation. Here's a
| thought experiment: someone puts two paintings in a
| photocopier and makes a single sheet of paper with both
| paintings. Did that person create art? They certainly had
| the vision to put those two specific paintings together,
| and they used a tool to create that vision in reality!
| card_zero wrote:
| It's going to be "creativity" (another hazy definition!)
| rather than effort, though. Photography, often said to be
| all about framing, seems very low effort. You might take
| one lucky snap. Then the effort can be claimed to be in
| _years of getting ready to be lucky,_ which is a fair
| point, but that displaced effort isn 't really in the
| specific photo. Besides, maybe you're a very happy
| photographer, loved every minute of learning your craft,
| and found it no effort at all, just really _interesting._
| tormeh wrote:
| Yeah, photography (editing aside) is about having taste
| and getting lucky. A good photographer can of course
| raise their odds of getting lucky, but still. There's
| some technique in there too, but that's really not all
| that complicated. That said, I think few things match a
| good photo. There's something about a photo subject being
| real that I find fascinating. A photo exhibition does not
| display the imagination of the photographers, but rather
| the incredible in the real world.
| RHSeeger wrote:
| It does, however, display the photographers ability to
| say "hey, you should see this" and be right about it.
| RHSeeger wrote:
| > Here's a thought experiment: someone puts two paintings
| in a photocopier and makes a single sheet of paper with
| both paintings. Did that person create art?
|
| Yeah, it gets really murky there. For that specific
| thought experiment, I would say it depends on if it's
| something that people will see and think about and talk
| about, etc. For example, a collection of pairs of images
| of people that were assassinated over the years and an
| image of their assassin would certain get people talking
| (some in a good way, some bad).
|
| When it comes to effort, I think that's only a factor,
| too; and not even necessarily a good one. There's art out
| there like
|
| - Someone taped a banana to a wall (and included
| instructions for taping another banana to replace it)
|
| - Someone (literally) threw a few cans of paint at a
| canvas and created something chaotic looking
|
| Both of those things are "low effort" at first glance.
| But someone spent time thinking about it, and what they
| wanted to do, and what people might think of it. And,
| without a doubt, there's people that would refer to both
| as art.
| card_zero wrote:
| Perhaps it has to be a more sophisticated emotion, such as
| feeling tired of a hackneyed definition.
| zelphirkalt wrote:
| I don't think it is about the feelings or emotions evoked in
| the observer. At least not in that generality. It only is, if
| there is an intention in the creating process of the art,
| that aims at evoking the emotions or feelings. Otherwise
| going by the more general definition, many everyday objects
| become art. Home becomes art. The way to the office becomes
| art, even if it completely sucks.
| greekrich92 wrote:
| If someone lies and convinces you that a loved one has died
| and you cry, were those feelings authentic?
|
| Art that provokes emotion in a cheap or manipulative way is
| often, if not always, bad art.
| CuriouslyC wrote:
| I'm pretty sure people have created images via random physical
| processes, then selected the best ones, and people have called
| it "art." That's no different than cherry picking AI generated
| images that resonate. The only difference is the anti-
| generative AI crusade being spearheaded by gatekeepers who want
| to keep their technical skills scarce in their own interests.
| zelphirkalt wrote:
| I think one could still point out a little difference: Random
| physical processes do usually not involve mix and matching
| millions of other people's works. Instead, something new in
| every aspect and its origin can emerge.
|
| It feels like AI art is often just a version of: "I take all
| the things and mix them! You can't tell which original work
| that tree is taken from! Tiihiiihi!"
|
| Where "tree" stands for any aspect of arbitrary size. The
| relationship is not that direct, of course, because all the
| works gen AI learns from kind of gets mixed in the weights of
| edges in the ANN. Nevertheless, the output is still some kind
| of mix of the stuff it learned from, even if it is not
| necessarily recognizable as such any longer. It is in the
| nature of how these things work.
| Demiurge wrote:
| I don't see splashes of primary color as more artistic. Anyway,
| what if you just ask it "more coarse"? I see impressive depth in
| the latest outputs, but as with all technically proficient
| performers, you might just have to consciously scale it back.
| raincole wrote:
| It's ridiculous lol.
|
| Midjourney is optimized for beautiful images, while Nano Banana
| is optimized for better prompt adherence and (more importantly)
| image editing. It should be obvious for anyone who spent 20
| minutes trying out these models.
|
| If your goal is to replace human designers with cheaper
| options[0], Nano Banana / ChatGPT is indefinitely more useful
| than Midjourney. I'd argue Midjourney is completely useless
| except for social media clout or making concept art for
| _experienced designers_.
|
| [0]: A hideous goal, I know. But we shouldn't sugarcoat it: this
| is what underpin the whole AI scheme now.
| jamblewamble wrote:
| It is what has underpinned all of human progress towards
| automation. It isn't a bad thing. Every time we automate
| something the luddites cry out about the coming mass
| unemployment. It has never happened.
| vlovich123 wrote:
| Except all the manufacturing jobs got shipped overseas and
| now those people are Walmart greeters or similar unskilled
| labor. Having a shit job isn't unemployment but it's not a
| huge step up
| loeg wrote:
| That isn't what happened. American jobs are more productive
| than ever. Americans are richer than ever. The modern
| luddites dramatically underestimate how bad the past was.
| pchangr wrote:
| It has happened. There is a related term we use which is
| related to a historical fact .. see
| https://en.wikipedia.org/wiki/Luddite
| loeg wrote:
| GP is saying mass unemployment caused by technology hasn't
| happened, not that the Luddites weren't a real historical
| group.
| pchangr wrote:
| Correct, and I am saying the Luddites were a group of
| people that suffered mass unemployment following a
| technological change. Specifically, the luddites were a
| group of 19th century textile workers that were left out
| of work due to the introduction of automated machinery in
| the textile industry. In other words, they are a perfect
| example of what GP claims hasn't happened.
| loeg wrote:
| A small group is not "mass unemployment" -- that's the
| point.
|
| > In a British textile industry that employed a million
| people, the [Luddite] movement's numbers never rose above
| a couple of thousand.
|
| https://www.cam.ac.uk/research/news/rage-against-the-
| machine
| coldtea wrote:
| The "never rose above a couple of thousand" small group
| refers to the number of activist Luddites. It doesn't
| refer to the people working in the textile industry in
| general - which was a big group, and which was heavily
| affected.
| JeremyNT wrote:
| The promise is to automate the drudge work, freeing people to
| pursue their passions.
|
| Like, you know... creating art.
| tekne wrote:
| I mean...
|
| There's the concept, and then there's the painting.
|
| AI slop from a generic prompt is not the same as "using AI
| to get my concept in physical form faster."
|
| Imagine, for example, a one-man animated movie. But, like,
| with a huge amount of work put into good, artistic, key-
| frames; what would previously have been a manga. That's
| _possible_ , soon, and I think that's huge and actual art.
| throwaway613745 wrote:
| > what would previously have been a manga
|
| Completely out of touch to downplay the entire manga
| industry as "skill issue".
|
| Akira Toriyama totally created Dragonball as a manga
| because he was just wasn't good enough to make an
| animated movie!
|
| Berserk is a book because Kentaro Miura just had skill
| issue!
|
| Only imagine if Tolkien wanted to create the Lord of the
| Rings if he had AI!
|
| As if a medium only artistic merit because sufficiently
| advanced technology just didn't exist yet. groooaaaaan
| coldtea wrote:
| Art will be created like AI - like it already got its hands
| on graphic design, and game art, and vfx, and music.
|
| It will leave not-yet-automatable grudge work to people
| instead.
| wombatpm wrote:
| But most work IS drudge work and the automation causes new
| different drudgery. Use to be you could dictate a letter
| and someone from the typing pool would clean it up, proof
| it, and send it. Now those same people get to write their
| own crappy email themselves
| malnourish wrote:
| What other automations have been hyped to automate and
| replace so many different types of jobs at once?
|
| Whether or not it comes to fruition, it's making large
| portions of society feel uneasy, and not just programmers, or
| artists, or teachers.
| pchangr wrote:
| The steam engine, for example
| elictronic wrote:
| Not finding a lot of sears and roebuck ads for steam
| engine driven girlfriends.
| dullcrisp wrote:
| You're got the wrong catalog.
| coldtea wrote:
| > _Every time we automate something the luddites cry out
| about the coming mass unemployment. It has never happened_
|
| It has happened each and every time, it just haven't affected
| you personally. Starting of course with the original luddites
| - they didn't complain out of some philosophical opposition
| to automation.
|
| Each time in changes like this a huge number of people lost
| their jobs and took big hits in their quality of life. The
| "new jobs", when they arrive, arrive for others.
|
| This includes the post 1990s switch to service and digital
| economies and outsourcing, which obliterated countless
| factory towns in the US - and those people didn't magically
| turn to coders and creatives. At best they took unemployment,
| big decreases in job prospects, shitty "gig" economy jobs,
| or, well, worse, including alcohol and opiods.
|
| With AI it's even worse, since it has the capacity to replace
| jobs without adding new ones, or a tiny handful at a hugely
| smaller rate.
| array_key_first wrote:
| It literally happens every single time - people DO lose jobs.
| They might get new jobs, but they definitely lose their old
| ones.
|
| And not everyone gets new jobs, because usually the new job
| is fundamentally different and might not be compatible with
| the person or their original desire out of their employment.
| stavros wrote:
| The problem isn't so much automation, but that the benefits
| of automation are invariably reaped by a few tech CEOs.
| It's not society in general that benefits, it's that the
| rich get richer, and the rest of us barely scrape by. If
| wealth were evenly distributed, nobody would bat an eyelid
| at AI.
|
| AI is not the problem. Late-stage capitalism and wealth
| disparity is.
| throwaway613745 wrote:
| > Every time we automate something the luddites cry out about
| the coming mass unemployment. It has never happened.
|
| It has happened every single time.
| pornel wrote:
| The author is using special prompts exploiting flaws of the old
| models, and doesn't like that new models interpret the hacks
| literally instead.
|
| The new models have prompt adherence precise enough to
| distinguish what "British Museum" or "auction at Christie's" is
| from the art itself, instead of blending a bag of words together
| into a single vector and implicitly copying all of the features
| of all works containing "museum" or "ArtStation" in their
| description.
| RHSeeger wrote:
| The prompts bothered me a lot, too. I don't do a lot of work
| with AI, but
|
| > A painting sold at Sotheby's
|
| and
|
| > A painting in the style of something that would be sold at
| Sotheby's
|
| convey very different meaning (to me).
| andy99 wrote:
| You're definitely on to something, people wouldn't criticize as
| much as they are otherwise, they'd ignore it.
|
| I think the whole point is that in optimizing for instruction
| following and boring realism we've lost what could have been some
| unique artistic elements of a new medium, but anyway.
| only-one1701 wrote:
| AI doesn't make art. The OP is trying to fit the square peg of
| their intuitive understanding about the art creation process into
| the round hole of generating it via AI
| jellyroll42 wrote:
| Correct! The process and struggle of creation is a large part
| of what makes art art. Removing friction from the process makes
| something artless.
| card_zero wrote:
| Yes, but: when I was young I used to love photorealism and
| hyperrealism, which is super-smooth-and-shiny art that
| conceals its process in order to awe simpletons. Then I
| bought an airbrush, and then true color computer graphics
| happened, and soon after that I began to appreciate brush
| strokes and the texture of pen marks and the idea of the
| personality of the artist's hand. But that doesn't mean the
| process-hiding stuff is non-art, or even bad art. What's
| wrong with creating an amazingly convincing illusion, wasn't
| that always the goal, historically? Also there are no prizes
| for effort, and if your artwork is _only_ struggle, I don 't
| want to see it. Unless you're really badass about it.
| nehal3m wrote:
| I really like Cory Doctorow's description of why it feels
| empty, quote:
|
| "Herein lies the problem with AI art. Just like with a law
| school letter of reference generated from three bullet
| points, the prompt given to an AI to produce creative
| writing or an image is the sum total of the communicative
| intent infused into the work. The prompter has a big,
| numinous, irreducible feeling and they want to infuse it
| into a work in order to materialize versions of that
| feeling in your mind and mine. When they deliver a single
| line's worth of description into the prompt box, then - by
| definition - that's the only part that carries any
| communicative freight."
| card_zero wrote:
| OK, but then there's the possibility of reestablishing
| the bandwidth by _selecting_ the output. If the artist
| selects one AI image from hundreds, that 's like
| photography, or collage, or "found sculpture" if you can
| dig it. Then we can do away with the need for hundreds of
| versions by saying that the artist selected this image
| from among _all the assorted sights seen during the day_
| to frame as art and present to the viewer, and that 's
| just like picking a preferred version from among
| hundreds, and thus is just like crafting an image.
| Tenuously. (This falls apart because the selectivity of
| the selection isn't good enough, I guess. But the process
| - throwing away bad ideas as you go along - is just like
| drawing.)
| nehal3m wrote:
| Sort of. It's like selecting from hundreds of versions of
| a letter of reference that word the same three bullet
| points slightly differently. It still feels empty to me,
| but I guess that's personal.
| card_zero wrote:
| I reckon it's not personal, and you and Doctorow are
| objectively correct, but the explanation isn't great.
| greekrich92 wrote:
| Art that takes tremendous effort but looks effortless isn't
| negated by my comment. The process and struggle is still
| there.
| chrismsimpson wrote:
| Is some kind of MoE or routing (but for image models obviously),
| depending on the prompt ask, a possible solve?
| TrueDuality wrote:
| I love the inherent wonder and joy in this post around the
| original images.
| smurda wrote:
| Another word for coarse is impasto technique, where the paint is
| so thick the painting-knife or brush strokes are visible and
| leave a pronounced texture (e.g. Van Gogh, Rembrandt).
|
| Another cool prompt could be specific painting techniques (e.g.
| pencil shading, glaze) as if you were training an actual artist
| in a specific technique.
| flir wrote:
| Just asked sora for an impasto image of a coca cola bottle. But
| it still came out looking like a coca cola ad/AI art. Super
| glossy, slick, meaningless. It didn't look like paint. (And the
| logo wasn't impasto, which I thought was interesting - I guess
| that logo's utterly ingrained in the model, it's seen it so
| many times).
| airstrike wrote:
| I'm no image gen expert but these prompts are downright terrible
| even by my standards.
|
| Are you really complaining that ", from the British Museum."
| leads to it a painting in the actual British Museum? Just remove
| the sentence, and you'll be fine. Now good luck trying to make
| Midjourney place the image at the museum!
|
| I'm a paying MJ user and am impressed by Nano Banana. They're
| different models. They each serve their purpose.
|
| This analysis is just noise. Yawn.
|
| Ironically, even an LLM with its fake reasoning capabilities can
| point out the issue with the prompts if you ask it to critique
| this article.
| wrsh07 wrote:
| It is interesting what the nbp model takes away from the
| prompt, though
|
| Eg instead of focusing on the artist, it focuses on the
| location
|
| This makes sense! I imagine it was trained in some sort of rlvr
| like way where you give it a prompt and then interrogate "does
| this image ..." (where each question examines a different
| aspect of the prompt)
|
| It's obviously an incredible model. I think there's a limit to
| how useful another article praising it is in contrast with one
| expressing frustration
|
| I would also welcome someone writing a short takedown where
| they fix the prompts and get better-than-2022 results from nbp
| delis-thumbs-7e wrote:
| Just fucking by canvas, brushes and good quality oil paint. You
| need only five colours[1]. Cost you maybe 50-80 euros. And any
| mess you produce will give you more joy thanand shot produced by
| any clanker brain. Keep at it for few years, take evening
| classrs, look tutorials and you have learned yourself a skill.
| You can now travel to any majos art museum across the world and
| have a discussion with masters through their works hanging on the
| wall.
|
| And you will also see how fucking sad and inferior all these ai
| images are. Really, trust me, please. There is more to art than
| this. There is more to life.
|
| [1] https://www.youtube.com/watch?v=f7F67FsLaaY
| BoredPositron wrote:
| The OP would likely prefer Disco Diffusion if they want their art
| to remain coarse. Modern models possess advanced spatial
| understanding and adhere strictly to prompts, whereas the OP is
| using unstructured inputs better suited for older models with
| CLIP or T5 encoders that lack that spatial awareness. These
| legacy prompting styles are incompatible with Gen3 models that
| utilize VLMs as text encoders. If the OP wants to explore modern
| architecture, they should use Flux.2 with a LoRA or perhaps a
| coarser model like Zit if they prefer to rely solely on text
| conditioning. Nano Banana Pro requires extremely long and
| distinctive prompting to achieve specific aesthetics. His blog
| post shows a lack of understanding and a lack of adaption to
| modern architecture which would be fine if it wasn't that
| dismissive.
|
| Here is an image from NBP with an adapted prompt for Italian
| futurism: https://imgur.com/a/4pN0I0R
|
| and for Kowloon:
|
| https://imgur.com/a/rDT8dfP
| dleeftink wrote:
| Eno applies:
|
| > It's the sound of failure: so much modern art is the sound of
| things going out of control, of a medium pushing to its limits
| and breaking apart. The distorted guitar sound is the sound of
| something too loud for the medium supposed to carry it. The blues
| singer with the cracked voice is the sound of an emotional cry
| too powerful for the throat that releases it. The excitement of
| grainy film, of bleached-out black and white, is the excitement
| of witnessing events too momentous for the medium assigned to
| record them.
| 2b3a51 wrote:
| And
|
| > "By the time a whole technology exists for something it
| probably isn't the most interesting thing to be doing."
| stephantul wrote:
| Where did you get this from? Searching for it, in a weird
| irony I guess, just leads me back to this post.
| cryzinger wrote:
| I recognize it as a quote from A Year With Swollen
| Appendices, which is a great read even if you aren't an Eno
| fan (although I am, which admittedly makes me biased :P)
| amram_art wrote:
| The problem is not in the image models rather the training data
| and its context. "British museum" for MJ is the image source,
| "British museum" is the setting for Nano Banana.
| yoan9224 wrote:
| The author's prompts are fighting against what Nano Banana was
| optimized for. Saying "British Museum" to MJv2 worked because it
| blurred all images tagged with museums into the aesthetic. NBP
| interprets it literally: show me something IN a museum.
|
| This isn't worse - it's different. MJv2 was a happy accident
| machine. NBP is a precision tool.
|
| If you want the coarse aesthetic, prompt for it: "rough
| brushstrokes, visible canvas texture, unfinished edges,
| painterly, loose composition". NBP will give you exactly that
| because it actually understands what you're asking for.
|
| The real lesson: we're in a transition period where prompting
| strategies that exploited old model quirks no longer work. That's
| fine - we just need to adapt our prompting to match what the
| model was designed to do.
| speedgoose wrote:
| Thanks ChatGPT. I'm wondering about the motivation to spam HN
| with LLM generated comments. Not the worst comments though.
| recursivecaveat wrote:
| Maybe it's better that this author is using LLMs because they
| would be an immensely frustrating client for an artist. Asks for
| futurism: complains about getting it. Wants bright colors:
| refuses to ask. Parts of the request are supposed to be evocative
| and parts are supposed to be literal, who knows which.
| efitz wrote:
| Why does anyone serious about art want to make art with AI?
|
| A large part of the magic of art is the human choices that go
| into it.
| userbinator wrote:
| Prompting an AI and then filtering the results _is_ a "human
| choice".
| effnorwood wrote:
| Peanut butter. Agree.
___________________________________________________________________
(page generated 2025-12-21 23:00 UTC)