Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stable Diffusion is a big deal

simonwillison.net

Post reply on HN
Print view View original

411–420 of 488 posts

Re: Stable Diffusion is a big deal

#411

Post by DethNinja »

tstrimple wrote: post #406
DethNinja wrote: post #401

Earlier quoted context omitted.

It takes 3 seconds to generate 1 image with my GPU. I can find a good prompt within 30 minutes to 1 hour. My GPU can generate 100 images in 5 minutes. Out of those 100 images, 10 is very close to what I exactly meant at professional concept artist level. So, in this case Stable Diffusion only working 10% of the time is fine. Future is already here, I’m already incorporating stable diffusion generated images to my pro…

What kind of GPU are you running this on? My 3080 seems to take about 30 seconds per image with 50 passes. I'm wondering if I'm missing out on some optimizations. Could just be the quality of Linux NVidia drivers.

That’s weird, I got RTX3070 on Windows.

Are you using 512x512 images or larger ones?

Best workflow is to keep images close to 512x512, record the seed and then upscale.

Re: Stable Diffusion is a big deal

#412

Post by a_t48 »

odessacubbage wrote: post #358
ChrisMarshallNY wrote: post #324

Earlier quoted context omitted.

It looks like a decent way to produce concept sketches. Currently, working with creatives (including programmers) is a very iterative process for non-creatives. "I want this." "No, I meant this." "Can we try making that line longer?" "Eh, I'm not feeling it. Why don't we try brighter colors?" "Ugh. That looks obnoxious. Can we tone down the red?" etc. If the non-creative can use this system to reduce that iteration,…

honestly i feel the opposite. one of the worst situations to run into as a designer is a client who is simply too married to a bad design. i would much rather work with something you scribbled on the back of a napkin than than some highly rendered ai vomit that is just fundamentally shit.

> character concept art on a napkin

https://labs.openai.com/e/bzJBnS0dkgvNeZ681ZTA49nK

Sadly, "highly rendered ai vomit" is filtered.

Re: Stable Diffusion is a big deal

#413

Post by ryandrake »

galdosdi wrote: post #394
eloff wrote: post #229

Earlier quoted context omitted.

As a new user of copilot for the last three months, I can't disagree more. I was initially skeptical, and I have noticed it often produces code that looks good but is wrong. However, it still saves me enough time each day to pay for the monthly subscription - in one day. That's a 30x ROI. I imagine it only gets better from here. I wont go back to programming without it.

Can I ask what kind of programming you do for it to be so helpful? I mostly do maintenance of legacy codebases (also known as codebases, lol) where a lot of the work is figuring out where the changes need to be made and actually making the changes is frequently just a few lines here and there. When I do have to figure out how to use some API, it's often not an open source one, so Copilot would not have it in its corp…

I haven't tried copilot either, but one of the things I'd be curious about is how well it can conform to a company's coding style guidelines and/or match its coding style with the existing legacy code that's being modified.

One of the major annoyances of working as a team with legacy code is when someone forgets to, or deliberately avoids, conforming their code to the style and techniques of the surrounding code. Nothing grinds my gears like working in a 500 line C++ file, where_every_function_uses_underbars, has consistent 4 space indentions, avoids exceptions, and passes by reference, but right in the middle is that functionThatMiltonWrote that uses camel-case, has 8 space indentions, throws exceptions, and passes-by-pointer.

Re: Stable Diffusion is a big deal

#414

Post by peoplefromibiza »

klipt wrote: post #12
throwaway1851 wrote: post #8

Earlier quoted context omitted.

There are really significant, novel copyright issues implicated by these large generative models trained on other people’s IP. If you take a step back, you can see that there are different ways to frame what is happening. One frame is: “Defendant built an algorithm that memorized features of Plaintiff’s IP. Defendant’s algorithm recombines parts of those features in order to produce works in the same domain that comp…

> “Defendant built an algorithm that memorized features of Plaintiff’s IP. Defendant’s algorithm recombines parts of those features in order to produce works in the same domain that compete with Plaintiff’s work, all without Plaintiff’s consent.” The fun part is, this is how human artists learn too.

> The fun part is, this is how human artists learn too.

We don't actually know exactly how human artists learn, and human artists are capable of innovation, nobody knew pointillism or Bauhaus before they were invented.

A little know fact is that for humans it takes a long long time to learn, while they learn, they develop a style, if they don't they are not "real" artists, but merely executors, artists evolve, sometimes dramatically, in unexpected ways [1] [2].

So for us humans learning is an experience, not just recombining parts of features of other things.

We are also highly influenced by feelings, unfortunately, so sometimes we do things a certain way because we felt that way, not because we wanted to paint that thing that way, or because we are not good enough to do exactly what we wanted to do.

Is Mona Lisa happy? Who can tell?

Was Leonardo happy when he painted it?

What was Leonardo thinking when he painted it?

What was happening in his life?

Is that the best smile Leonardo could paint or it's an enigma he put there for future generations?

These questions are more important for an artist than the mere features of the painting.

The philosophical question is: is art discovered or invented?

If it's discovered, then SD can generate art, if it's invented, than SD it's not even generative work, because to invent something from something else, you need inventiveness.

[1] Picasso 1896 https://mymodernmet.com/wp/wp-content/uploads/2018/01/pablo-...

[2] Picasso 1946 https://www.photo.rmn.fr/CorexDoc/RMN/Media/TR1/MS4GY/16-515...

Re: Stable Diffusion is a big deal

#415

Post by TchoBeer »

joshuahedlund wrote: post #295
geofft wrote: post #291

Earlier quoted context omitted.

Yes, but the consequence for society is that professionalization is coming to every single field, and the blue-collar jobs are evaporating, and we had better figure out how to get all those people either white-collar jobs or some other form of income if we want to avoid significant social instability. It used to be that you could find work as a political cartoonist and draw a picture of some satirizable politician ea…

> blue-collar jobs are evaporating I've been hearing this for awhile, yet ironically right now we have the biggest shortage of blue-collar workers we've had in a long time.

It's gonna happen in 10 years, every year.

Re: Stable Diffusion is a big deal

#416

Post by shagie »

roywiggins wrote: post #373
shagie wrote: post #351

Earlier quoted context omitted.

I can see this replacing the clip and misappropriated art in slide presentations that no one is paying for currently with a $20/month service that lets you do "line art angry man in toga at computer" to put into your talk on Kuberentes. It might replace the "nice pic, do you have it at {size} so I can use it as a desktop image" comments on various social media sites. I don't see it replacing an actual photograph as a…

> because they are subtly wrong in some ways Well, they are now . Give it a year and we'll see.

Possibly... but I'm skeptical. For the type of photography that I do, these are things that come from an understanding of the world and its implications. You aren't going to see certain types of clouds in certain landscapes - they just don't form there. For example, having a cloud that indicates fast moving wind in a mountain environment in a plains landscape with a glassy smooth pond.

It's not that you can't paint that picture... but you'll never be able to capture that scene in camera. If someone was presenting that as a photograph, it would feel wrong to me because of an understanding of the meteorological criteria for the scene.

I believe that they will generate images that are impressive. I watch https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg and have been impressed with the pace of technology.

Yet, I am doubtful that I'll have a generated image at 11x17 that holds up to the same scrutiny that I apply to my own photographs.

I am absolutely certain that it will be able to generate images that are completely appropriate for images that you don't look at for more than a minute at a time or are used as complimentary material for other content.

All that said, I am not concerned that I will get more or less sales of my photographs with AI generated art competing. The people who are going to pay for a photograph are going to pay for a photograph. Those who aren't - weren't going to in the first place.

Re: Stable Diffusion is a big deal

#417

Post by peoplefromibiza »

Workaccount2 wrote: post #399
peoplefromibiza wrote: post #389

Earlier quoted context omitted.

> But legally your friend has no legs to stand on. My friend is just upset. Legally he has every right in the World, he's the author for Christ Sake! Will he try anything? Of course not. Are you okay with this? Well, then you should reconsider your values. > People do "like copies" of works all the time, If those copies are authorized, I don't see the problem. Try to recreate a Star Wars image and sell it on the Inte…

>Would you bet your life on the fact that it doesn't? Yes, because that's not how it works. If your friend is still upset, maybe they should consider the artists they "stole" their learning material from.

> Yes, because that's not how it works.

I think you don't know how laws and Author rights work

The simple fact his work became part of something else he did not authorize is the problem here.

And yes, it could spit out something that is very close to the original, so close that fair use could not stand.

Fair use is not a right!

> If your friend is still upset, maybe they should consider the artists they "stole" their learning material from.

He does, don't imply differently, ad hominem are a stupid argument for very stupid people.

That's why he spent 30 years of his life learning and in the end he became good enough to meet the artists he "stole" from to thank them of what they did.

You seem to lack the ability to understand the difference between being a good person and being a senseless automata...

Re: Stable Diffusion is a big deal

#418

Post by tstrimple »

DethNinja wrote: post #411
tstrimple wrote: post #406

Earlier quoted context omitted.

What kind of GPU are you running this on? My 3080 seems to take about 30 seconds per image with 50 passes. I'm wondering if I'm missing out on some optimizations. Could just be the quality of Linux NVidia drivers.

That’s weird, I got RTX3070 on Windows. Are you using 512x512 images or larger ones? Best workflow is to keep images close to 512x512, record the seed and then upscale.

I'm using 512x768 as the default, but a quick test shows only a marginal difference in speed between the two. I'll have to give Windows a try to see if it's the driver holding me back. Do you have any tips or resources for up-scaling the image after?

Re: Stable Diffusion is a big deal

#419

Post by peoplefromibiza »

dsign wrote: post #385
peoplefromibiza wrote: post #339

Earlier quoted context omitted.

> I would venture to guess that the author doesn't have a full understanding of what the AI is doing or how it works. Actually he does. > There are a gazillion artist who take clear inspiration from other artists Inspiration is not the same thing Stable Diffusion does. We can't even define inspiration in a proper manner, but for sure we can say that if someone wants to draw comics in the way Tezuka made them, they ha…

I think that your and your friend's argument reduces to "the AI is not a human, but a machine-like, and thus can not be `inspired' but only `reproduce'". I don't know if it is a novel argument to be tried in a court of (copyright) law, but it is certainly a good one.

> I think that your and your friend's argument reduces to "the AI is not a human, but a machine-like, and thus can not be `inspired' but only `reproduce'".

That's the one argument, but it's not the most important important.

The most compelling issue here is that SD used copyrighted data scraped from the Internet without even informing the authors, who were not unknown to SD authors, because they tagged them in the model.

Re: Stable Diffusion is a big deal

#420

Post by TchoBeer »

shinycode wrote: post #251
systemvoltage wrote: post #138

Earlier quoted context omitted.

I always wondered if we massively overestimate human creativity. Maybe it is ingrained in our culture and our very being. I’ve never heard counter arguments that humans are not that creative. Creativity demonstrated by Alpha zero chess engine blows Magnus Carlsen’s mind (from his recent interview with Lex Fridman), I wonder if at some point in the future, we’ll finally throw in the towel and get out of the denial pha…

Without trained models from human creativity, what can AI do ? These AI emerged because of human creativity. Picasso created it’s new art form from its own creativity. He created something no one ever though of before. Now AI are fueled with Picasso’s drawing and can produce art that looks like his maybe. But what about creating something entirely new that has never been fueled into the engine. Could the AI invent so…

I think it's undeniable that AI can create novel things, the question is if AI can create novel things that are also interesting. A randomized 600x600 png is novel, but it isn't at all interesting, much of what goes into making a piece of art interesting is not a quantifiable or well-defined goal. That's not to say that AI is better than humans, just the opposite, art is a deeply human object, and I do not know if we would appreciate art made and developed by AI in the same way we do absorbing and creating art in response to each other.
Post reply on HN