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

251–260 of 437 posts

Re: Stable Diffusion Public Release

#251

Post by peoplefromibiza »

aortega wrote: post #249
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…

>make a hyperrealistic pornographic image of you with a gorilla[0] I don't understand this irrational fear. This can be done today, just need some minutes instead of some seconds to create a good Photoshop. Also, seriously this is the thing you fear? fake porn? there are much worse thing you can do with this tech, like phising, falsifications, etc. Not mentioning leaving millions of graphic designers out of job.

Unfortunately Anything that can go wrong will go wrong

Photoshop is a skill, not very widespread as we assume.

Typing something is literally at everyone's fingertips.

Re: Stable Diffusion Public Release

#252

Post by dustyleary »

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

There are a few different kinds of 'secure enclaves' implemented on chips, where you can have some degree of trust that it "cannot" be faked.

E.g. crypto wallets, hardware signing tokens, etc.

We could imagine an imaging sensor chip made by a big-name company whose reputation matters, where the imaging sensor chip does the signing itself.

So, Sony or Texas Instruments or Canon start manufacturing a CCD chip that crypto signs its output. And this chip "can't" be messed with in the same way that other crypto-signing hardware "can't" be messed with.

That doesn't seem too far-fetched to me.

* edit: As I think about it, I think more likely what happens is that e.g. Apple starts promising that any "iPhoneReality(tm)" image, which is digitally signed in a certain way, cannot have been faked and was certainly taken by the hardware that it 'promises' to be (e.g. the iPhone 25).

Regardless of how they implement it at the hardware level to maintain this guarantee, it is going to be a major target for security researchers to create fake images that carry the signature.

So, we will have some level of trust that the signature "works", because it is always being attacked by security researchers. Just like our crypto methods work today. There will be a cat-and-mouse game between manufacturers and researchers/hackers, and we'll probably know years in advance when a particular implementation is becoming "shaky".

Re: Stable Diffusion Public Release

#253

Post by egypturnash »

redavni wrote: post #210
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…

Eh...the countdown to Photoshop and Blender integrating AI support has already started.

I wanna punch everyone involved in that, too.

Admittedly as someone who's been subscribing to Creative Cloud for a while I already wanna punch a lot of people at Adobe so the people working on this particular part of Photoshop are gonna have to get in line.

Re: Stable Diffusion Public Release

#254

Post by MaxikCZ »

api wrote: post #67

"This release is the culmination of many hours of collective effort to create a single file that compresses the visual information of humanity into a few gigabytes." If something like this is possible, does this mean there's actually far less meaningful information out there than we think? Could you in fact pack virtually all meaningful information ever gathered by humanity onto a 1TiB or smaller hard drive? Obviousl…

You can pack virtually all meaningful information ever gathered by humanity onto a single bit, but its gonna be lossy. And what is your definition of "meaningful information" anyway. Meaningful today might not be meanigful yesterday. Nobody cares about spin of each electron in my brain today, but in 4 centuries my descendants will be like "if only we had that information, we could simulate our great-...-great parent today"

Re: Stable Diffusion Public Release

#255

Post by matheusmoreira »

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…

> you can fully expect your asshole friends to grab a dozen photos of you from Facebook and then make a hyperrealistic pornographic image of you with a gorilla

... Someone is gonna do this to children. This technology is gonna end up on the news. Maybe they'll even try to ban it.

Re: Stable Diffusion Public Release

#256

Post by cerol »

aortega wrote: post #249
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…

>make a hyperrealistic pornographic image of you with a gorilla[0] I don't understand this irrational fear. This can be done today, just need some minutes instead of some seconds to create a good Photoshop. Also, seriously this is the thing you fear? fake porn? there are much worse thing you can do with this tech, like phising, falsifications, etc. Not mentioning leaving millions of graphic designers out of job.

That's what I was thinking. Whether a pornographic picture of me and a gorilla was made by photoshop or AI is irrelevant. People's reactions will be the same, and repercussions will be mostly the same (which doesn't means there will be consequences).

If someone really wants to hurt you, not having AI isn't going to stop them.

Re: Stable Diffusion Public Release

#257

Post by egypturnash »

cercatrova wrote: post #229
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…

I mean I get what you're saying, sucks to have someone or something take your job, but isn't this a neo-luddite type argument? AI is gonna come for us all eventually.

Please save this comment and re-read it when a new development in AI suddenly goes from "this is cute" to "holy fuck my job feels obsolete and the motherfuckers doing it are not gonna give a single thought to all the people they're putting out of work". Thank you.

Re: Stable Diffusion Public Release

#258

Post by ALittleLight »

fezfight wrote: post #66
egypturnash wrote: post #41

Earlier quoted context omitted.

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

Kinda like the creation of copilot and it's ilk for programmers, and gpt3 for writers. Ive seen some talk recently around 'prompt engineers'... Probably to some extent, every job will become prompt engineering in some way. Eventually I suppose the AIs will also do the prompts. At which point I hope we've all agreed to a star trek utopia, or it's gonna get real bad. Or maybe it'll get way better.

I think right now we could setup the AI's to do the prompts. You type in a vague description - "gorilla in a suit" and that is passed to GPT-3's API with instructions to provide a detailed and vivid description of the input in X style where X is one of several different styles. GPT-3 generates multiple prompts, the prompts passed to Stable Diffusion, the user gets back a grid of different images and styles. Selecting an image on the results grid prompts for variation, possibly of the prompt and the images.

Re: Stable Diffusion Public Release

#259

Post by marak830 »

nelsondev wrote: post #153
bluejellybean wrote: post #131

Earlier quoted context omitted.

My personal hunch is that this will end up leading to a situation in which presenters do a cryptographic handshake that works to verify and prove authenticity. This isn't a new idea, and it has some very obvious drawbacks, but I don't see much of a way around the issue. The handshake could work great for something like official news releases, but for other instances that might come up in court, say, dash cam footage…

Looking forward to a future where all a politician’s quotes are on a blockchain, signed by their private key, and they chose to do so voluntarily out of fear of deep fakes. Will remove all the useless “I didn’t say that”

It will end up back where we started, "it's not on the Blockchain so I didn't say it", while making racist remarks with friends.

Re: Stable Diffusion Public Release

#260

Post by andybak »

treis wrote: post #241
andybak wrote: post #140

Earlier quoted context omitted.

With all due respect, I've been using it for over a week and I don't think you've given it a fair shot. There's plenty of cases it's worse than Dall-E and there's plenty of cases where it's better. Overall it seems to show less semantic understanding but it handles many stylistic suggestions much better. It's definitely in the right ballpark. In fact I'm still using a wide range of models - many of which aren't regar…

Can you give an example? I've done: A house painted blue with a white porch A dreamy shot of an alpaca playing lacrosse A red car parked in a driveway The last one was particularly crappy. It gave me a red house with a driveway, but no car. And the house wasn't even really a house. It superficially looked like one but was actually two garages put together.

Here's some random prompts I've had nice results from:

    iridescent metal retro robot made out of simple geometric shapes. tilt shift photography. award winning

    Scene in a creepy graveyard from Samurai Jack by Genndy Tartakovsky and Eyvind Earle

    virus bacteria microbe by haeckel fairytale magic realism steampunk mysterious vivid colors by andy kehoe amanda clarke

    etching of an anthropomorphic factory machine in the style of boris artzybasheff

    origami low polygon black pug forest digital art hyper realistic

    a tilt shift photo of a creepy doll Tri-X 400 TX by gerhard richter
I guess I might have spent more time reading guides on "prompt engineering" than you. ;-) I think maybe Dall-E is more forgiving of "vanilla prompts".

However I do get nice results from simpler prompts as well. I just tend to use this style of prompt more often than not.

Post reply on HN