back
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?
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.
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.

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?)
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?

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.
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.
Do neural painter next!

https://github.com/reiinakano/neural-painters-pytorch

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?
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
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.

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.
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.

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!

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.

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

I wonder how art experts would assess these paintings in a blinded experiment ("blinded" figuratively, of course ;-)
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!
I think modern art is not about creation, it is about ability to sell.
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.
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

https://vcloud42.com/file/art42-cdn/cubism/seed_0000086582.j...

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://gregorywieber.com/art/a-walk-through-latent-space-mak...

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
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.
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.

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

http://blueboxsw.com/labs/shogun/play.cfm?S_Key_Play=281C436...

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? :)
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.
Just an infinite stream of dead picture links, right now. I suppose something is down?
This is awesome. There's a business here somewhere.
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?