Hacker News new | past | comments | ask | show | jobs | submit login
Show HN: A stream of AI-generated art (art42.net)
277 points by valentinvieriu on Feb 16, 2020 | hide | past | favorite | 187 comments

Author Here: Just wanted to share some technical details. The code can be found here https://github.com/valentinvieriu/stylegan2 The main code and modification were put together by https://github.com/pbaylies/stylegan2. I've started with the pretrained ffhq model, and I've trained it using come hand picked 1000 images of cubist Wikiart paintings.

The frontend is Vuejs and it's using the amazing https://github.com/Akryum/vue-virtual-scroller for the very fast infinite scroll option. The app runs on Cloudflare Workers, using https://github.com/l5x/vue-ssr-cloudflare-workers-template

Hope you guys enjoy the experience and would love to get some constructive feedback

I think you have an opportunity here --- I found myself wondering how much it would cost to get a nice-quality print on canvas or metal. Something I could hang in my office. They look that good. Are they (or could they be) generated in sufficiently high resolution for a large format print?

Working in an office decorated by a bot is the most demoralizing experience I could imagine. I would probably go into an existential rage and start breaking things until someone more physically powerful came and subdued me.

It can be worse you could also work on SAP, like the author (No harsh feeling/flame war ; thank you to the author for this artsy experience ; but I couldn't help but notice this, I believe, relevant context).

To me these pictures are very nice looking from afar, but once you try to look in the details it makes you feel stupid that you don't get it, until you realize that it is senseless, there is no coherence, no point, no soul and it's normal that there is nothing to get from the picture as it's not in the algorithm.

The technique is perfect. But the art side reflection and emotion must still come from the eye of the beholder. It is deeply moving art in the sense it inspire strong negative emotions, the feeling that there are some stronger forces coming to crush you.

One such reflection that these collection should inspire is : "Is this the direction we want to take ?". Infinitely many garbage art stealing attention away from human artists.

Don't get me wrong, I like generated art but it's necessary to situate it in its context. That what makes it interesting. I even believe you can have machine explore thing and discover interesting thing on their own without it being formulaic, but we are not there yet.

Your SAP remarks are funny and somehow true (maybe), but I'm maybe one of the lucky guys. I work for an interesting Labs section inside SAP (https://cxlabs.sap.com/) and we are lucky enough to do research on some interesting topics.

I don't fully agree with you on the purpose of art. Art can create different meanings for every watcher and they could be quite far away from what was the intended purpose ( the message ) of the artist. I would say that main function of art is to ask questions, and also to give you a way to experience life in a way you would otherwise not be able to. In this context I think AI generated art can bring something new, a new layer of reality, a new set of questions, that might not been surfaced because we use brains to create art and brains to interpret it. It could be a new type of input that would push humanity further.

I think that postmodern view on art has fallen out of popularity. It’s silly to abstract away the artist and kinda pretend there may as well not be one, and that the full meaning may be purely in the sensory matter... because this leads to an “everything is art” perspective: everything in the field of my senses at any point is art. Which is preposterous for “art” to tell me that my senses are meaningful because I can ask questions about them and learn something. Thank you, art, for intervening to add a completely vacuous annotation on my experience.

These pictures are interesting though. To me the thing that popped out, without having read background on the project, was how this robot artist is copying modernists like Picasso and possibly Pollock and DeKooning. And doing it along a few themes, with high degree of repetition; or tweaking some small things in each variation. The limitations are glaring and I’m wondering will it evolve and how.

> To me these pictures are very nice looking from afar, but once you try to look in the details it makes you feel stupid that you don't get it, until you realize that it is senseless, there is no coherence, no point, no soul and it's normal that there is nothing to get from the picture as it's not in the algorithm.

My train of thought exactly. Even second-rate/beginner/hobbyist paintings, like those on Binned Art for example, are absolutely crushing these in every dimension.

Is your problem that you know its bot-generated, or that you think there's some flaw in the pictures?

What if you didn't know that the painting was the work of a bot?

What if it was just some abstract painting that someone took enough fancy to to pay to have put on a canvas?

Personally, I couldn't really tell them from the human-generated wikiart pictures that seeded the algorithm. Those human-generated pieces didn't speak to me either.

I'd love to see the algorithm work on some other art style seeds.

I'd say it depends. For me art is as much about the artist behind a specific piece as it is about the actual piece. I agree with the person you responded to. I want human feelings in my art, no matter how abstract, for it to truly speak to me!

Playing devil's advocate: it sounds like you're deluding yourself ;)

Perhaps the Vogels https://en.wikipedia.org/wiki/Herbert_and_Dorothy_Vogel knew the artist? The way they amassed their collection is truly inspiring.

Picaso's wife infamously knew he was having an affair with his muse from glancing at a painting. But did every other Picaso fan who saw that same painting? Did truly know anything about the artist behind the picture?

So the chances of everyone else who appreciates an artist actually truly knowing anything about the actual artist? Complete rubbish, say I!

Take Turner, for example: turns out, the location of a lot of his pictures have been wrongly attributed! How everyone can claim to 'know' the artist and yet not realise that the picture is of Portsmouth or a lake in Scotland instead of Venice or somewhere else seems like they didn't really know the artist after all?

So there's a picture on the wall by Satoshi Nakamoto. You feel that genuine, because it's signed? Then when you get told that its painted by a bot, you feel cheated? Because you felt you knew something about the artist by looking at the art?

Having bot-made art in the office just gets me asking all the wrong questions like "What is this? Why is it here? Why am I here? What am I doing with my precious finite time on earth? Why did they automate the creation of art? Why didn't they automate my job?"

Ironically a human artist who could evoke a response like that would be doing better than most.

Those seem like difficult questions, and maybe we don’t usually want to grapple with them, but they don’t sound like the wrong ones.

One might argue that there is plenty of human feeling in this bot-art. After all, it's trained on art with human feelings. Seems like it might be a very effective way to propagate it. It's a sort-of dispassionate third party who finds the thread common to all of the cubist pieces in the training sets.

Such as a security bot?

Sure, once those things are common place it'll be dystopian; but for now it's just a fun conversation starter.

This sounds like a plotline of a Ligottian short story.

Tbh, with direct printing to (large) canvas being reasonably priced now, this could be an easy sell

Especially if they can be generated at 300dpi+

Well the resolution is good enough.I've gave it a try and looks quite good on a 50cmx50cm canvas. You need to upscale it once or twice with a Super-Resolution AI algorithm

So meta

I've added the option to print now. Feel free to give it a try

In the spirit of the effort, might as well complete the value stream and just hang a big display. Very cool project tho'

You can use a super-resolution tool like https://letsenhance.io/ to upscale the image which might make it better for printing.

Hey this is an awesome project with really cool results. I think it can be grouped with "found art" conceptually. Several of the generated pieces are really quite interesting, though at some point the styles seem a bit repetitive, though I imagine that's simply due to training on cubism.

Great idea. Looks very convincing and aesthetic to me, but I am not an art expert. But I do know a lot about music and I am not yet convinced of the current offers of AI in this regard. So it would be very interesting to know how art experts react to these paintings.

I'm not an art expert or an artist, but I spent a lot of time in art galleries and museums forty years ago looking closely at and thinking about abstract art. Some of the pieces here strike me as remarkably good and interesting to look at. If they had been implemented in oils rather than pixels, they would not seem out of place on museum walls.

That would be the next step to close the circle https://twitter.com/sougwen/status/1218672595350032385/photo...

The challenge is that the Latent Space ( the space of all the art pieces of this model ) is so HUGE ( technically is infinite ) that there could be masterpieces sitting there undiscovered. I was aiming to create an interface to allow for crowd sourcing this process of finding those masterpieces. Hope the ui and and easy to pick some favorite process will help

Or... train AI to pick out the masterpieces...and loop.

Well people have to create the training dataset so we're on that path, should the author choose to continue on it.

Yep. Please click on the favorite button :) so I can keep the favorites

Why cubist?

Is it that that's the style of art you like?

Or that you found to work best?

It would be really interesting to see the kind of images generated when its trained with other styles.

I have other styles too, and I'm planning on exchanging the AI on a regular basis. This was the one that I've personally liked the most. It was also the one that required the least training. I only have a 2080ti, and those models are quite hard to train. If you have recognisable shapes ore faces, you can quickly create some very disgusting art pieces that will make people sick. At this moment abstract seems to be the best solution.

Really great project. I'm interested in how you've implemented the back-end? How did you productionize the GAN model? Or did you just pregenerate 1000 images? (ie. are the images generated on-demand?)

So the backend is simple, i've chosen to pregenerate 1 mil images at the beginning so it gives you some idea of diversity. I"ve tried to generate them realtime, but my server would have not survived the hackernews popularity today. The gan model is created by me, see in the comments above. I'm planning on bringing up new images on a daily timeframe, keep the one that people choose as favorites and delete the ones that were not popular

Fascinating stuff.

Who decides what gets shared? Are you posting everything, or do you curate the results of the algorithm?

What is the input to produce one of these images (aside from the pre-trained model)?

Is it a random number or another image or something else?

Let's say you wanted to re-render the exact same image given the same state of your pre-trained model, what information would you use here?

Yes there is an initial seed that it's needed, and it's baked in the name of the file. So if in the future I'll find a way to improve the quality, you can get the same result by passing in the seed

Very cool. Some of the results reminded me of Max Ernst’s frottage works and futurist compositions. If you are interested in exploring this with other curated collections, reach out to me. I have a MOMA collection of about 10k images.

Would really appreciate it! Please connect with me on twitter @valentinvieriu

This is awesome! I would hook this up with Shopify and one of those printing and shipping services and see where that leads you. I'm a Shopify expert, already did that for customers, if you need advice let me know

I would love to see TensorBoard learning curves from your experiment: score/real and score/fake. I've tried fine-tuning FFHQ-model before and training was not progressing as I expected it to.

Interesting idea. I will give it a try to see what is the output. I was looking for something in this direction to make the brush feel more appealing. Thank you

What I think would be interesting would be to add a human discriminator test: Can you tell genuine cubist art from computer-generated cubist art?

What would the point of that be may I ask? Something to do with a Turing like test? Lets not forget that the would be cubist model is actually fed tons of cubist images and all it does is regurgitating that back. Art done by people is somewhat similar but it does take place in a context that which AI could not yet understand.

Well, I'm personally curious. When I looked through this thread several hours ago, there seemed to be two very distinct camps: "This is really cool you should see if you can sell these", and "This is just random stuff mashed together; there's clearly no artistic intent". The first group, it seems, sees no "artistic intent" in real cubist art, and so sees no difference; the second claims to be able to see real "artistic intent" in real art, and to note its absence here.

I have to admit I'm rather in the first camp. I have spent time in art galleries, but not a huge amount; I have opinions about art, but 90% of what I hear said about paintings seems to me to be nonsense.

I know a lot about music; and so far I've always been able to distinguish 100% of computer-generated musical snippets from genuine classical snippets. And specifically, the key difference is exactly what is claimed by the second group -- that computer-generated melodies are just piles of similar musical ideas mashed together, without any apparent intent or direction.

One of the claims of skeptics of art is that there really is nothing there, and that all the "art critics" are just doing a wetware version of GPT-2. If someone trained in art can really distinguish a cubist painting with artistic intent from one generated with this neural net, then it's 1) proof that there really is something there, and 2) it's maybe worth learning about.

Not trying to denigrate the amazing technical skill needed to make this thing, but from the point of view of someone who makes art, this is a pastiche image maker. I have yet to see AI generate anything that's not a combination of existing images and techniques. Probably wading into murky philosophical waters here but I reckon art needs to be more than a nice 'arty' looking image to be considered any good. If you are going to make Art that is worth the capital 'A' on the front, then it has to mean something. However I suspect the days of actually making Art are in the past. We're on to something else now. Not necessarily better or worse, just different. Art is an old idea, not entirely relevant any more.

Not trying to denigrate artists, but as somebody that admittedly doesn't appreciate art, I'm still not sure how artists aren't just pastiche image maker themselves. Based on your comment, I'm not entirely clear what the difference is


Watch this video of an art dealer looking at the "efforts" of the Top Gear trio - He's looking for premeditation, emotion, and inspiration, it's arguably a bit pretentious, but you can see his change in the thought process when James May starts to explain how his big metal face is a deconstruction of a car into a display of his emotions while driving it.

A piece of art is different to different people, but you are consuming the artist's opinions both directly (if you are aware of the artist's previous work, i.e. Francis Bacons paintings are pretty interesting if you know a bit about his life) and indirectly (The Video game Pathologic is very polarising but is so utterly alien to the archetypal video game - especially when it first came out - that it really resonates with some of those who play it). Imitation and technique only go so far - Erik Satie wasn't particularly well regarded as a composer (or even a musician, he often referred to himself as a Phonometrician) when he produced his most famous works but he is known to this day for his command of minimalism, repitition and a surprisingly Jazz-like use of "horizontal" harmony from simple scales (Potentially constructed by stacking triads but I don't know)

Well said. I actually do appreciate many forms of art, but I feel that many artist (that I know) are just a mixture of regurgitators and expert salesmen. They make something random, then come up with a backstory that makes it somewhat interesting. This AI can out perform them, without the need for the ingenuous hook story.

The serious ones who stick around doing the same thing for a lifetime do eventually find some meaningful essence however abstract that is. But there is indeed a lot of deception in the art world since it is a non quantifiable subject the story does add some value

> I actually do appreciate many forms of art, but I feel that many artist (that I know) are just a mixture of regurgitators and expert salesmen. They make something random, then come up with a backstory that makes it somewhat interesting.

I wouldn't call your relationship with art "appreciation". Sounds more like undisguised disdain.

I appreciate art, not artists. You seem to either have misread what I said, or are actively trying to misattribute my words.

> "I appreciate art, not artists."

  Can you have one without the other ?

  Apparently, now, you can...

Interpreting the random is a fair form of art. Like a sports commentator or video game mechanic.

(pastiche: I had to look it up)


  n 1: a musical composition consisting of a series of songs or other musical pieces from various sources [syn: medley, potpourri, pastiche]

  2: a work of art that imitates the style of some previous work

A lot of art is exactly that, but it's usually very obvious. As it is in these pictures.

I find this whole discussion quite interesting: There seem to be many people who think these photos are pretty much just like what you see in an art gallery, and others who say that it's obviously just inspirationless imitation.

Comparing this to generated music -- every time there's a "quiz" challenging to distinguish computer-generated snippets of music from real classical music, I've gotten 100%. The key difference is that the computer-generated music I've heard so far is just one musical idea after the other; it doesn't seem to have intent or motion. (Much like GPT-2 style text: a single sentence looks reasonable; once you get to several paragraphs, it completely stops "hanging together".)

> it doesn't seem to have intent or motion

Because it does not have any. It’s a tool. Can we say a cool brush creates paintings, a complex instrument creates music? By itself Im afraid it’s far from it. A human hand must be involved somewhere (im literal about the hand part, but a brain nonetheless)

Can this machine, beautiful art though it may make, look at the work of the cubists and spontaneously generate Gehry?

Without Mondrian, would it find beauty in clean abstract lines and sharp angles? Can it, by itself, come up with the concept of neoplasticism and implement that, in any way, to create a new beautiful artwork?

Would the AI, not for Klimt, have an appreciation for how casually erotic the female form can be?

Does it, yet, have this appreciation?

I don't know, and I'm sure it doesn't either.

> I don't know, and I'm sure it doesn't either.

Even more pertinently, it doesn't care.

I might stretch it further that it can’t even care because the machine does not have the capability to care.

I think to the average human, that was implicit in my comment, but for the benefit of the machines, it's good to spell it out.

I agree with you. I think the reason AI hasn't made anything but derivatives is in part because machines are not sentient. 100% of AI is machine learning, there is no heart or conscience.

However art is anything that moves you and the paintings on this website are most definitely moving to me. I find them terrifying and a lot of that has to do with the fact that a machine made them.

There isn't anything really grotesque there. (Grotesque is a blend of horror and empathy. Horror is a scary guy in a mask holding a bloody axe or things jumping out at you. Grotesque is a person maimed.)

This site has, in my opinion, art that is nauseatingly scary. It is scary in part because its soulless and part because it's a mirror of how a machine sees humanity.

Regardless of how it was made, it moved me therefore from my perspective: It is art.

> 100% of AI is machine learning, there is no heart or conscience.

And, because AI implies heart and/or conscience, ML is a much better term because it is more accurate and describing.

Very well stated

There really is something nauseating or repulsive about this. I've had the same feeling with other ML generated images. It's alien and familiar at the same time.

It reminds me of this nightmare that was making the rounds a while back: https://sea.mashable.com/culture/3430/people-cant-figure-out...

It is only familiar because it was trained on familiar work.

I’ve been exploring this space and find myself thinking of Andy Warhol. I would definitely consider him an artist. A great one even. But his work was quite different from Picasso. Warhol had a factory. His silkscreens were often done by assistants. It said something about the Modern Industrial Age. His work raised questions about authorship, authenticity, etc.

I found myself thinking about similar things when I trained a neural net to make art: who’s the artist? Me, or the machine?

When did art ever require purpose? Who decides what is and isn't art? Very tricky path to trod down.

In this case, you decide. You click that Favorite button and it's a decision you make. The AI artist has a set of rules that learned from the previous trained art pieces, but the final shape, and the final decision is yours. You like it or not, and it's quite personal too.

it isn’t possible to create something that doesn’t serve a purpose. what “good” artists and other art professionals have that makes them experts is 1) an understanding of this fact, then 2) knowledge of semiotics and history among other related areas that afford as deep an understanding of potential meanings as possible — this is the tricky part, because it requires real work

I thought one of the ideas was to build into this a way to let people pick the good stuff.

Which is to ask if Audiences are never wrong?

What if I make the argument I think this art is more beautiful, because of the interesting way it was generated?

Relevant quote from Feynman about art: https://www.goodreads.com/quotes/184384-i-have-a-friend-who-...

I like art too and make some myself (musical). But I happen to think art is just what each viewer thinks of it. I don't know enough about visual art to know whether this is a "pastiche image maker", though I suspect AI won't make that for long, if it is.

All art (and innovation, really) is about combining existing things in new and unexpected ways. Doesn’t matter whether it’s a machine or person that creates the end result, the art is in the process.

It’s just that with machines and deep learning we can try more variations in a much shorter period of time.

No more waiting to see whether that bunch of disaffected art students sitting around drinking absinthe and smoking strong cigarettes come up with anything good, get a bunch of computers to do it in a fraction of the time - and with far less angst.

Those computers don’t really think. Whatch what you wish for, future might just look like that.

That art moves person who sees it is more important than how original it is.

Originality is how artists signal to their peers and scene their value. It's relatively modern concept. Art existed before originality was considered a value and it probably exists after the originality stops being an issue.

I have yet to see 99.999% of artists "generate anything that's not a combination of existing images and techniques". As mere mortals are not in a position to hang the works of 0,0001% that can this AI art can be a reasonable alternative.

I wonder, based on your comment, what the output would look like if the training was inverted. Anything that looks like art would skew towards zero, for instance.

That would be intersting

This is indistinguishable from something that would be hanging in an art museum, and anyone pretending otherwise only believes so because they know a priori that it is generated by ML.

Honestly I would consider buying something like this, though I'd never waste my money on something so pretentious from a human. This, however, is an achievement, and there's beauty in that.

Edit: in fact, if love to see two tests: a blind test with a series of humans, and a classifier trained to differentiate between machine and human generated art. I have no doubt that the humans would not score much better than chance - I bet only an artificial discriminator would be able to tell, and then only because of subtle differences in pixel distributions that humans won't perceive. Throw in a couple different GANs trained on different distributions and even a machine will have trouble telling the difference!

"This is indistinguishable from something that would be hanging in an art museum."

Haha, the exact opposite of my scroll through. I thought to myself: "These look like a clone stamp sampled and then vomited up all the lovely modernist paintings I've seen at art museums."

Yes, my first thought was "reconstituted art"

My first thought was “hotel lobby”

This is indistinguishable from something that would be hanging in an art museum, and anyone pretending otherwise only believes so because they know a priori that it is generated by ML.

I certainly couldn't distinguish an individual images from something I might see in a museum. At the same time, scrolling the images felt very different than scrolling through a series of images by a given artist or images from a given show.

This is what an image search for cubists and wikiart looks like. Also feels very different.


Which is just to say this sequence feels different. I couldn't tell if it's better or worse. It does feel bleak, opaque, oppressive, washed-out. All that is something some art aims for. But it could just be the randomness of the pictures, like they're well-spoken words in a language I don't know.

The images are somewhat closer to abstract "composition" pieces, which are literally studies on visual composition:


I think this is quite expected, since ANN constructs its own view on stuffs, which is basically deconstruction of images into local components, like local color relation and sub-patterns. Global composition and shapes will be destroyed in favor of local composition, which is pretty much what many modern abstract paintings were after.

While ANN can mass-produced stuffs like this, that doesn't mean it's gonna replace artists. It's gonna be the opposite: if artists learn through AIs, each of which trained on different sets of data (which can overlap), we will be able to see works in a different level. It's like go players study AlphaGo for new principles that humankind have missed.

Thanks for the reference! I think you've reminded of the vocabulary needed to express my impression of the images. IE, That's definitely how the images feel - just texture and composition.

The thing is that I think that art involves using texture to "say" something. The artist puts combines represent of the physical world with reference to previous artists and images with composition. Some artists stress one or the other of these things - so that, yeah, a pure composition painting can definitely be "good enough to be in a museum". But a stream of painting like this definitely doesn't feel a museum or art as a whole.

Imagine a forum of artists talking about how a WYSIWYG builder rivals anything a dev can build.

Yep, this. Think we should stick to the tech behind the idea.

Whilst these all the samples seem to have decent form, use of colour and space, one can quickly see derivate concepts and images from more famous original works and an excess of 3D forms. There's also a challenge in understanding the meaning of each painting. Also, a lot of penguin type shapes for some reason.

One of the tests you describe - a classifier trained to differentiate between machine and human generated art - is exactly what the ML GAN model is doing.

The generative adversarial network (GAN) has a generative part and a discriminative part which compete with each other. The generative model creates the images that you see in the gallery. The discriminative model tries to predicts whether an image is real or was generated. When it starts failing often, we know that the generative model is getting better (of course, the details are much more complicated).

I don't it's fair to call it pretentious if from a human but beautiful if from a computer. You even said it yourself

> ... anyone pretending otherwise only believes so because they know a priori that it is generated by ML.

To me, a large part of an artworks beauty comes from its ability to make me feel something. These works make me feel nothing at all. So I cannot call them beautiful.

Do paintings by elephants make you feel anything?

The only reason these are indistinguishable from "pretentious" paintings is because those were used for a training set. Use a "non-pretentious" set and you will get corresponding generated art. Particular images generated are almost not the point, in my opinion.

Many human paintings make me feel nothing at all.

I'm reminded of https://www.ba-bamail.com/content.aspx?emailid=24569. Someone please make a similar test of "modern art vs ML-generated art".

I answered 18 correct answers out of 20. Do I qualify as an art critic now?

I assume that the AI generated art would be harder but what is the point really? I would only see the point if the model was trained with something else and ‘it came up with modern art looking images’.

And this works because modern art is flexible enough to allow all kinds of things. Why not do the test on generated text? AI still fails terribly on that mainly because it is not sentient, it does not actually understand anything of it

You could always scale down the image so that the clsssifier “sees” on the same scale as a human...

The further down the page I scrolled, the more I got a kind of despair. To realize that the space was infinite, and I would never reach its end. Each individual image is pretty cool. As a collection, they're sad.

What's funny is that I then tabbed back to HN, where I was deep down the comments tree, and momentarily I forgot that real humans make these comments. I thought "I shall never reach the end of the HN comments. It's all AI - generating a pastiche of plausible opinions and sentences-that-appear-sentient." Same despair. Quite a relief, then, to get to the end of the page.

Interesting, so would you say that the infinite aspect helped out the experience or damaged it? I've had doubts first when I've introduced it ( more from caching perspectives and data transfer costs ). But then I've wanted to showcase this amazing feature of those networks of generating an infinite amount of unique items, and also offer an unique experience to every user, the possibility of seeing unique art and bookmarking / printing it if considered

I guess there's a time premise to a painting. The artist is not necessarily asserting -- but I implicitly assume -- that the artist deems any given painting "a thing upon which to dwell." A stamp of good aesthetic housekeeping -- trust me, says the painter, your viewer's mind and soul can rest herewithin. I mean, the painter certainly did. Day upon day of slowly creating the thing in which their visual cortex swam, lived, breathed and had its being.

I am standing next to the artist. Seeing what she saw, imagining what it must be like to arrive from the other direction, without all the layers of preconception and intention that she baked in. And hopefully, from her direction and from mine, the good housekeeping seal, there is something "good" about this meeting of two perspectives.

Your project throws that good-housekeeping seal out the window. Which is not to say that a given image is bad. Rather, that the social contract between one viewer and one artist, is missing. My viewer's eye keeps assuming it exists, and my brain reminds me -- no, this is all fake, there is no humanity behind the curtain. There is nobody to connect to. Maybe it's still art, but not the kind I... emotionally expect from a thing that looks, at first glance, beautifully painted?

So, the infinite aspect definitely "helps" the experience. The exhaustion helps one feel viscerally how big is the problem space.

Isn't that something a 'bot would say.

These comments are not all made by people. I'm obviously a bot. Come on.

Now we just need an infinite stream of AI generated art criticism to tell us how to talk about it at parties.

"It's a master stroke of heartache, brutality, and redemption." - Lexus book club commercial

I get the appeal from a "it's fascinating we can make computers do this" stance.

I don't get the appeal as trying to appreciate this as actual art (or music in the case of ai-generated tunes).

Art for me is about the connection I can make with the person who made it. I can't make a connection with an algorithm. I view it and I am like "OK this is interesting" but that's about it. There's no desire to try and understand it because it was programmatically generated.

Does anyone else feel this way?

Yes - I don’t think it’s a stretch to say that most people who appreciate fine arts feel this way.

Tech is more of a, “why is a painting of a triangle worth so much!?” crowd (see: other comments).

Given that this is the product of human written code trained on art generated by other humans, you are seeing something that’s an amalgam of what humans have done.

You can’t take away the human and get what you have here.

What about connecting with the person who wrote the algorithm? Imagine a time in which music was only heard when performed by the right group of people. Without that the appreciation was mostly for a cultural memory or written record of the music. There are more ways to connect with art and it's maker than playing back the audio or opening the image.

I think Mario Klingemann said it the best. https://vimeo.com/298000366 This becomes just a tool, like everything else

I can appreciate the algorithm, and have appreciated in the past, if there are artful qualities to it, but in this case it isn't quite apt to say that as we are talking about the output of the algorithm, not the algorithm itself.

Out of curiosity, do you feel that an artwork having an anonymous author substantially detracts from your appreciation of it?

No, because the art allows me to get to know the person. If an anonymous voice tells me a short story I enjoy, I still get to appreciate the qualities of the person's storytelling (almost a completely lost art these days)

Would you appreaciate these images if you thought they were made by a person?

Machine learning enthusiasts always treat this response as if it's a checkmate, but it's a silly stance, you are depending on either:

a) the ignorance or apathy of the person answering the question; and/or

b) deception if you are telling them it's created by a human, when it's not.

There's less inherent value of this kind of "art" for most people if they know it's created by an algorithm in milliseconds, rather than by a human artist who spent hours working on it. Maybe there is an audience who would pay good money for it, who knows. But I think most human beings would devalue it if you were honest about its source.

I don't think it's silly at all; I couldn't determine whether this was specifically made by hand or with the aid of a computer, even when put next to a piece that was (it's the amalgamation of real arts afterall).

I can't appreciate how much pain something takes if it can be achieved for less. Much like opting to use a bucket for water transport instead of pipes, it's just silly.

> I can't appreciate how much pain something takes if it can be achieved for less. Much like opting to use a bucket for water transport instead of pipes, it's just silly.

That's a valid point of view I think from the point of the art consumer, if you are into computer generated art. But misses part of the point of art completely; the point from the artists' perspective, at least for humans, which is about self-expression.

I never really understood why people want to know so much about an artist, and not just appreciate the art, in itself.

If the artist has such a great story, I wish they (or someone else) would just write a book about them, and do without the art as an intermediary.

Because we are human beings. Art is just as much about connection as much as it is about technique.

how about... you pretend they're just from an infinite amount of anonymous authors?

some of them feel pretty real to me, but then again, I don't know a thing 'bout this...

were someone to make a catalogue of them, with random names and possibly authors, would you not enjoy it then, too, if you believe them to be made by humans?

Unfortunately, as an adult, my fantasy I create for myself will only take the enjoyment so far. I need some things to be based in reality at some point.

I wonder how art experts would assess these paintings in a blinded experiment ("blinded" figuratively, of course ;-)

I'd bet most of them are quite "low quality art", but interesting anyway... plus, afaik, generally the image itself is not that important, as is the story behind it, if you have a story, a black square is a masterpiece, if you don't, it's junk...

OK so next step train AI on story generation for the art :)

The "story" aspect of art is bullshit, unless the art itself tells that story in a tangible way. If there's a story behind a black square, it's still just a black square.

I disagree.

A piece is more than just itself, there is a history to each one and that story adds to the piece. Some (honestly most) pieces and stories just are not very interesting, maybe even to the artist, and that is fine. And some are interesting to just some people at some times.

Art 'speaks' to each person differently, or sometimes not at all. Art is what you make of it. If you make nothing of some forms of art, that is on you. If you make nothing of all forms of art, you may want to consider why so many other humans feel so strongly the other way.

Though pretentious, ArtAssignment on YT is a great into to the wider world of art. I really think you should give it a try:


Is this a portent of truth's final days? Is absurdism the only final, knowable truth, in a world where only fact carries meaning, as humanity has been deconstructed and rendered noumenal? The voices of a million potential future artists just cried out in agony and were silenced forever. The Tesla CEO has it right. AI is the end of humanity -- but (probably) not in a SkyNet sort of way, but one that is much worse because it renders the term "hope" itself meaningless.

This is fantastic! Wrap it in a SmartTV app and sell it for a dollar or two as a monthly decorative art subscription!

Noted down! Tv targeted app :) Is like a fireplace app, but with art

Perfect for the Samsung Frame for instance

I think modern art is not about creation, it is about ability to sell.

There are certainly cases where this might be true, but I doubt that this assumption is generally true; one would have to do some experiments and put these artificially generated paintings up for real auctions (for the purpose of scientific knowledge, of course, not to cheat).

I've tried this around with some friends of mine and they could not spot the difference between Person generated and AI generated. None were art experts just people with good taste.

Well, there is a considerable difference between "good taste" and professional experience with the art market. A lot of art sales are made with things that are totally tasteless from my unprofessional perspective. It would therefore make a lot of sense to experiment with real art experts with experience of the market. Maybe you have heard of the experiments where they submitted machine generated publications to scientific conferences and succeeded with it ;-)

Was this on a screen or some sort of physical medium (canvas, etc.)?

Hence the saying:

"Art is anything you can get away with."

Still a human hand is involved there, even for mere deception.

You're right. But it is not a particular trait of modern art. It was the same centuries ago as well.

Good point! So what it needs is a story then? How about the work, is it interesting?

I like the work very much. The art market is very much about story. Check out a documentary (I think available on Netflix') called Beltracchi: The art of Forgery which wrestles with this question.

So what is about creation?

We train algos on creation and we think AI nailed it

Would be more intersting explaining the computer what art is, give it some hints and let it come up With something. This is all but a gimmicky remix of previous work, whatever was trained on

I don't think anyone has found a way to explain to people what art is, let alone computers. Practically all art is very heavily inspired by what has been done before, even if as a kind of rejection of it. The only exceptions I can think of are "art" by toddlers, chimpanzees, pigs, etc., and it's debatable whether that fits the definition (or whether the definitions it fits are acceptable).

Agreed. But all art takes place within a context which an AI algo cannot ever fathom of. AI is nothing but a tool and lets squeeze this down to a simpler tool, could a brush ever create art by itself?

To my untrained eye, many of these images are as good as anything else I've seen from humans. What qualities make me say that? Your images create a visceral response. They evoke a lot of interesting thoughts and feelings. If anything they remind me of 20th century modern art. Very impressive stuff. It'd be amazing to make these bigger, ensure texture is there, print them large like an oil painting.

The lack of texture is the issue for me.

I need more $$ to feed the GPU monster, and then you will get more texture :) This is more of technical issue that can be solved quite easy, but you are right, most of them lack details and texture.

I love this idea of generated content. I'm wondering what artists thinks about that.

There was a recent Show HN project about generate quotes having some great results having sense : https://machineswisdom.com

The results are really impressive.

I have been studying art non-professionally for the past 5 odd years now and I would be hard pressed to tell you if any one of the pictures your software generated was created by a human artist or not.

Nice work!

This one is amazing


It reminds me of those time slice type photos, where the bottom is when the little 'tree' on the right is young and each layer is a new year or three along the way, in which the environment gets a bit older and gnarlier over time.

Absolutely wonderful work.

Site appears to be down at the moment. Some shameless self-promotion since there appears to be some interest in this, I recently trained a StyleGAN model on Fauvist artists:


http://www.sanbase.com/ - these were created long before AI became a household name. Actually no AI involved at all. All just pure math. Think it is called "generative art" or something to that tune

generative art is of a completely different tune... even if for this style they might not be that different results, the neural net(s) here (the "AI") can have details and textures simple math cannot, such as I saw a horse head in one, some other things in others...

but it's still very cool, even if the site may or may not be slightly deteriorating (top banner's broke for me, wouldn't be surprised if some other stuff was too)...

I myself did procedural texture generation at one point. There are also commercial packages. This was long time ago so I am not sure in what state those commercial offerings are now. Still you'd be amazed what kinds of textures can be generated procedurally. Definitely not anything less the AI can come up with. At least from what I saw on that AI site.

"Site broke on me" - interesting I did not notice anything. Maybe because we might've used different browsers

The process is a little different here. You can also put no Man Sky in the same category of procedural generated universes

I realize that. My point was that in my opinion AI in this case does not add anything more "artistically" speaking.

I'd argue nobody can add anything not a combination of other things

They look great. If you make something where people can pick say paintings/styles they like, and then you generate custom for them until they choose one (and presumably then un-watermark or high res it), you may have a business here.

Ok. What’s the point of that, original poster or canvas print? In a way training AI on existing art and generating some more amounts to vulgarizing abstract art or art in general and doesn’t add much to it, it is a gimmick. It certainly looks attractive but does it have any real value?

Have you ever seen things like fractals on people's walls? They are curiosities. I guess you could call them gimmicks, but I would just call them interesting--gimmicks has kind of derogatory tone.

Value is just what people will pay for it. Which is apparently, in some cases, more than 430k: https://www.nytimes.com/2018/10/25/arts/design/ai-art-sold-c...

The notion of vulgarizing art is what people said about jazz when it pulled people away from the "fine art" of classical (the "swamp of jazz"). How wrong they were. I don't think people will see beautiful art, albeit generated by an AI, as "vulgar" in the future.

No no, fractals are not gimmicks. Theres a beauty in mathematical relationship that can be greatly appreciated and taken in. On the other hand this is stats of existing work remixed. Looks pretty but hasn’t got a lot of value. Yes, could be printed on canvas if that helps. Could eventually finds its way in IKEA because it does look pretty and does have some ornamental value. Question is, would anyone hold onto any particular piece for 100 years or more?

Im not saying the same thing, Jazz was still done by people within a context of its times. AI currently cannot do that. Maybe AGI will..

Or taking lots of photos and selecting the one with the decisive moment in it? People create 'art' like that all the time. It's art because I say it's art, it may not be someones else's idea of art. The artist (even an AI) and the the viewer form a system and art is the result. Would one of these be art in the middle of the forest? Or a Leonardo?

Reminds me of Debris by a NullSoft employee. It would download random pictures using a search engine, and it would craft it together. The end result is unique, and allowed you to look into the details. You could even edit the search terms or the result, add cameos (some vague nudity, for example). What I found really funny though, is that the end results often had actual funny easter eggs. I guess if you add up all of this randomness, and you watch closely, the chances of something funny being included increase. It just might take a while till you find it.

Looks exactly as "modern art" to me.

I do not appreciate modern art anyway, but I love this since it will for sure upset some artists that think they're talented.

Liking something because it will negatively affect other people is a weird position to take

I love cubism and this plain sucks. You see clearly that is not human work, there is no subject, there is no meaning, there aren't emotions...is garbage.

So.. the very same sentiment people had when they first saw cubist art made by humans...

Allow me to mix it with one of my projects to show you a better way to display:


Impressive on the surface. but, with a general idea of how the art was created, I fail to gain emotion, resemblance, or some form of appreciation that I've felt from certain art before.

Still, I guess "art" is all subjective anyway & this is still great stuff.

warhol would have been all over this

What do you like about the latent space that you are sampling from? :)

It's not a particular space, is just random. I'm hoping that by having more people randomly checking the space, more masterpieces will surface

This looks fantastic! Amazing that it is possible to make an AI output images that you want to hang on your walls.

I like these. It feels like the paintings version of lying in the grass trying to find images in the clouds.

This is my grim little friend in green coveralls and a green hat. Maybe he is confiscating some masks.


Just an infinite stream of dead picture links, right now. I suppose something is down?

This is awesome. There's a business here somewhere.

It would be great if it would be :) At this moment is just an art experiment

If I were you, I'd build this:

- An interface where people select a subset of artists they like. - Build a model on the fly with art just from those artists - Get HQ high res downloads of generated art

Freemium model, with 1 HQ download free and the then $1 per download.

The written code to create these images has a copyright, but the generated images themselves do not.

Doesn't AI generated art violate the whole definition of art?

This is a good question, I dunno really.

On one hand is art really art without the bullshit story of the maker that defines the art? Sometimes we really want the creator to shut up making bullshit stories and just enjoy what has been made.

On the other hand, is a AI algo really a form of being creative? Nature is an algo that creates things.

Do things have to be art to appreciate their beauty? Is art about beauty? Is art about statements?

etc. etc.

Probably all answers are personal really.

Depends on how meta you want to be. This output requires skilled application of software development and aesthetic judgement. You could call that the 'art'.

Or maybe it's synthetic art or simulated art.

Either way I feel it has value.

I think Mario Klingemann said it the best. https://vimeo.com/298000366 This becomes just a tool, like everything else

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact