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

Stable Diffusion Public Release

stability.ai

Post reply on HN
Print view View original

301–310 of 437 posts

Re: Stable Diffusion Public Release

#301

Post by egypturnash »

bottlepalm wrote: post #277
egypturnash wrote: post #266

Earlier quoted context omitted.

Yeah, if we're gonna replace every fucking profession with a half-assed good-enough AI version, what're we even here for? We're sure not all gonna survive in a capitalist society where you have to create some kind of "value" to earn enough money to pay for your roof and your food and your power. IIRC there is some vague "it sure got real bad" somewhere in the Trek timelines between "capitalism ended" and "post-scarci…

Next let's get rid of all the artists and replace them with AI. Redistribute their skills so we can all make art. Oh wait that just happened. You're a hypocrite that wants to redistribute the wealth of others, but not your own. Also joking about murdering people is bad taste and not how you convey a point or win an argument. Very low class.

No post body was provided.

Re: Stable Diffusion Public Release

#302

Post by AJ007 »

mrshadowgoose wrote: post #298
mabbo wrote: post #33

The most interesting part, to me, of a release like this is the amount of "please don't abuse this technology" pleading. No licence will ever stop people from doing things that the licence says they can't. There will always be someone who digs into the internals and makes a version that does not respect your hopes and dreams. It's going to be bad. As I see it, within a couple years this tech will be so widespread and…

> The most interesting part, to me, of a release like this is the amount of "please don't abuse this technology" pleading. > Why bother asking people not to? I guess if it helps you sleep at night that you tried, I guess? I've perceived this as them doing the necessary amount of virtue-signaling and ass-covering to avoid the ire of groups that are loud/powerful enough to cause issues for them in the short-term. I've…

I never saw it create anything more NSFW than female boobs. It won't generate penises or genitals besides mounds of hair. Right now the "NSFW" flag/filter is 99%+ false positives. This is stuff that used to be allowed in G-rated movies in the US.

True to both Stable Diffusion and Dalle2, the more encompassing the content of your image is, the more incorrect the detail is. Both generally will make fantastic faces but anatomy and consistency starts falling apart with full bodies. Contorted limbs, missing fingers, too many limbs, etc. No one is going to be fooled here.

Of course the models could be trained on offensive images and over a long enough time period eventually will. But, for now, someone is going to have to spend millions of dollars on compute and have the human expertise behind it too. Then again, if we had an image generator making pictures of [insert X offensive thing] that is a whole lot less disgusting than the plentiful real photos and videos of that thing in reality.

Re: Stable Diffusion Public Release

#303

Post by cercatrova »

egypturnash wrote: post #300
cercatrova wrote: post #263

Earlier quoted context omitted.

Look at that, you said the same thing to me 8 days ago [0]. I'll stick to the same rebuttals you got for that comment as well, namely that AI comes for us all, the only thing to be done is to adapt and survive, or perish. Like @yanderekko says, it is cowardice to assume we should make an exception for AI in our specific field of interest. [0] https://news.ycombinator.com/item?id=32462157

Yeah, I'm saying this to everyone who tells me to suck it up. Eventually this line ain't gonna work when the only job left is AI researcher.

We have a long way to go until then.

Re: Stable Diffusion Public Release

#304

Post by egypturnash »

quadcore wrote: post #297
egypturnash wrote: post #157

Earlier quoted context omitted.

It's my fucking job. I've spent my whole fucking life getting good at drawing. I can probably manage to keep finding work but I am really not happy about what this is going to do to that place where a young artist is right at the threshold of being good enough to make it their job. Because once you're spending most of your days doing a thing, you start getting better at it a lot faster . And every place this shit get…

This feels so wrong this AI thing, strangely enough Im not that stressed. Look at the recursive side of it its hilarious. Im an artist. AI is around. Do I want to put my work online? No. So no artists put stuff online anymore? So how does future of art work exactly? Will send booklets by mail again? There is the democratic side of it. We the people ultimately decides. Those pictures are generated by using artists wor…

Yeah going offline begins to look tempting except for the part that huge amounts of how you get people to want to pay for your work is by sharing it publicly. Except then someone can come along and scrape it all and dump it into their AI training black box without giving two shits about copyright.

Re: Stable Diffusion Public Release

#305

Post by emporas »

mabbo wrote: post #33

The most interesting part, to me, of a release like this is the amount of "please don't abuse this technology" pleading. No licence will ever stop people from doing things that the licence says they can't. There will always be someone who digs into the internals and makes a version that does not respect your hopes and dreams. It's going to be bad. As I see it, within a couple years this tech will be so widespread and…

Well we will be able to generate satirical political images of politicians, of religions easily and quickly. So there are some upsides for the technology to be given to every comedian out there. Politicians and religions, did have an easy ride the last few years, so we must set the record straight from now on.

Some fear porn was thrown out when GPT-3 was released. I love GPT-3, i used it just yesterday it is very good. I am just wondering when the total destruction of the world will happen because of GPT-3.

Re: Stable Diffusion Public Release

#306

Post by AJ007 »

earth_walker wrote: post #296
mabbo wrote: post #33

The most interesting part, to me, of a release like this is the amount of "please don't abuse this technology" pleading. No licence will ever stop people from doing things that the licence says they can't. There will always be someone who digs into the internals and makes a version that does not respect your hopes and dreams. It's going to be bad. As I see it, within a couple years this tech will be so widespread and…

I think you don't give enough emphasis on the "if you even could before" part. Sure, this makes realistic fakes easier and more available to to the masses. So what? We've had the technology to 'frame' people in similar ways for decades now, and other than entertain the 4chan teens it does squat. There's enough money interest in bringing down certain politicians, if faking a sex tape or back-room conversation would ma…

These images are good for satire, spoofs, and comedy but they definitely won't be fooling anyone.

Re: Stable Diffusion Public Release

#307

Post by LouisSayers »

seydor wrote: post #226
zone411 wrote: post #225

Earlier quoted context omitted.

It'll be hard to deny crypto-signed photos https://petapixel.com/2022/08/08/sonys-forgery-proof-tech-ad... , especially if they include metadata that distinguish photos of AI generated images from normal photos.

any camera can be hacked to plant an image in its framebuffer

In which case if found out will result in that person / publishers credibility going down the drain.

We will learn to trust sources (cryptographically signed) rather than just what we see.

Re: Stable Diffusion Public Release

#308

Post by davesque »

nerdponx wrote: post #248
davesque wrote: post #237

Pretty cool. Although it's interesting that it can't seem to render an image from a precise description that should have something like an objectively correct answer. I tried prompts like "Middle C engraved on a staff with a treble clef" and "An SN74LS173 integrated circuit chip on a breadboard" both of which came back with images that were nowhere close to something I'd call accurate. I don't mean to detract from th…

I am generally of the "it's not threatening yet and won't be for a while" camp, but in this particular case it's probably just for lack of trying. These algorithms are essentially enormous pattern-matching engines, so given enough data and some task-specific engineering effort, I wouldn't be surprised if you could build an "AI" circuit designer, like Copilot but for electronics instead of code. Next-level autorouting…

Sure, but this model is a general image synthesizer that is trained on a massive amount of data that is openly available on the internet. Given that, I would assume that it would have seen many images of 74xx series chips and also musical notation. So I would think that the most "likely" image to generate would involve either a chip with 8 pins on either side (for the 74ls173) or a note on a single leger line just below a staff with a treble clef. I imagine there must be hundreds of 74xx chip images that would establish that fact and also thousands of images of musical notation that would establish the other.

I guess the takeaway really is that the model does not function in such a way that it can recall its training data. Which is fine. I don't think I should expect it to. On the other hand, GPT-3 can be made to produce specific facts that are established by its training data. Although, admittedly it often gets things wrong. Maybe the problem of image modeling is just naturally harder than language modeling. After all, language already "directly" represents meaning in some sense much more than arbitrary images do.

I'm sure someone could design a targeted model that would solve the issues I'm talking about. But I feel as though they shouldn't have to if we really had something that sees the world the way humans do. In any case, this work definitely seems cutting edge and represents a huge leap in that direction.

Re: Stable Diffusion Public Release

#309

Post by cshenton »

derac wrote: post #171
daenz wrote: post #30

Earlier quoted context omitted.

>This is one of the most important moments in all of art history. I agree, but not for the reasons you imply. It will force real artists to differentiate themselves from AI, since the line is now sufficiently blurred. It's probably the death of an era of digital art as we know it.

Making art is already not making much money for the vast majority of producers (outside of 3d modeling). There really aren't very many jobs in making art. I'd reckon most people are artists because they love doing it.

This is completely wrong, the digital art industry is enormous and, mind you, pretty uniformly pissed off that this model has been trained off of their non public-domain work.

Re: Stable Diffusion Public Release

#310

Post by emporas »

squeaky-clean wrote: post #76
egypturnash wrote: post #41

Earlier quoted context omitted.

It’s the opposite of exciting if art is your job, lemme tell you.

I have a friend who works as an artist and he's excited and nervous about this. But also he's trying to learn how to use these well. If you try these AI out, there's definitely an art to writing good prompts that gets what you actually want. Hopefully these AI will become just another brush in the artist's palette rather than a replacement. I hope these end up similar to the relationship between Google and programmin…

I have a friend who paints, google/ athanasart. His paintings are usually purchased before they are even finished, and sometimes even stolen. All of that technology, Dalle2, Disco diffusion, Stable Diffusion, is totally boring to him. He doesn't even care. He will not install this technology to his machine, or use it online, even if he is paid to do it. I love Craiyon, Dalle2, Stable Diffusion, but just beautiful images, are not art.
Post reply on HN