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

211–220 of 437 posts

Re: Stable Diffusion Public Release

#211

Post by seydor »

OmarIsmail wrote: post #72
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…

We do a decent job of banning child pornography. And bringing the two ideas together, is child pornography that is provably created by an AI still illegal?

Actually ... we just did a good job of making generated child pornography ubiquitous.

Re: Stable Diffusion Public Release

#212

Post by seydor »

gjsman-1000 wrote: post #29
hunkins wrote: post #3

This release changes society forever. Free and open access to generate a hyper-realistic image via just a text prompt is more powerful than I think we can imagine currently. Art, media, politics, conspiracy theories; all of it changes with this.

Eh... if I was making conspiracy theories, it's not like Photoshop hasn't existed for decades already, with far more predictable results.

This is like a gazillion photoshops being released in the wild. Things change with scale, and there is a threshold where, if enough people start doubting often enough, then all the people will doubt all the time

Re: Stable Diffusion Public Release

#213

Post by mempko »

neurostimulant wrote: post #186
vintermann wrote: post #161

Earlier quoted context omitted.

You need a decent GPU, though. I suspect my 6080MiB won't cut it any longer :(

You're going to need at least 10GB VRAM. My SFF pc with 4GB VRAM can only run dalle mini / craiyon :(

Not if you change the precision to float16. Should work on a smaller card. Tried on a 1080 with 8GB and it works well.

Re: Stable Diffusion Public Release

#214

Post by punkspider »

Tenoke wrote: post #193

I'm getting a 403 on the Colab (while successfully logging in and providing a huggingface token). Is it already disabled? Do you have to pay huggingface to download the model? It's unclear from the Colab and post where the issue is.

The solution seems to be to visit https://huggingface.co/CompVis/stable-diffusion-v1-4 and check a checkbox and click the button to confirm access.

The full error I also got was:

  HTTPError: 403 Client Error: Forbidden for url: https://huggingface.co/api/models/CompVis/stable-diffusion-v1-4/revision/fp16
I visited https://huggingface.co/api/models/CompVis/stable-diffusion-v... and saw

  {"error":"Access to model CompVis/stable-diffusion-v1-4 is restricted and you are not in the authorized list. Visit https://huggingface.co/CompVis/stable-diffusion-v1-4 to ask for access."}
Eventually I focused and realized I need to visit that URL to solve the issue. Hope this helps.

Re: Stable Diffusion Public Release

#215

Post by tshaddox »

seydor wrote: post #208
tshaddox wrote: post #121

Earlier quoted context omitted.

That seems unlikely, given that making up hurtful stories about people and transmitting them via text or voice is still a thing. Everyone knows that anyone can make up any story they want without any technology whatsoever, and yet spreading rumors is still a thing.

Not really. I can't think of a recent "leaked texts" that the participants cannot not easily and plausibly deny (e.g. elon's supposed messages to gates), or even voice messages. Even most images can already be denied as photoshop if all the witnesses agree. The only medium that is somewhat hard to deny is videos, like sex tapes, but that's also not too hard. I think there will soon be a race to make deep learning pic…

Perhaps that's somewhat true for famous people, although there are plenty of examples of false stories (without any forged evidence, literally just stories) causing real embarrassment and damage to reputation.

But it's even more true for non-famous people getting bullied in their social groups, both online and offline, and that's more what I was responding to (the "asshole friends" in the original comment).

Re: Stable Diffusion Public Release

#216

Post by kelseyfrog »

dinosaurdynasty wrote: post #162
nelsondev wrote: post #153

Earlier quoted context omitted.

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”

Do politicians understand blockchains?

Neither do we[1], so it's sort of a mixed bag.

1. True for an overwhelming majority of the body politic.

Re: Stable Diffusion Public Release

#217

Post by drexlspivey »

badsectoracula wrote: post #44

Is there any way to download this on my PC and run it offline? Something like a command-line tool like $ ./something "cow flying in space" > cow-in-space.png that runs with local-only data (i.e. no internet access, no DRM, no weird API keys, etc like pretty much every AI-related application i've seen recently) would be neat.

Yes but you need a GPU with 10Gb of vRAM

Re: Stable Diffusion Public Release

#218

Post by visarga »

jmfldn wrote: post #115
archagon wrote: post #99

Earlier quoted context omitted.

Why would people want to consume art that says nothing and means nothing? While this technology is fascinating, it produces the visual equivalent of muzak, and will continue to do so in perpetuity without the ability to reason.

That's the problem for me too. This tech is cool for games, stock images etc but for actual art it's pretty meaningless. The artist's experience, biography and relationship with the world and how that feeds into their work is the WHOLE point for me. I want to engage, via any real artistic product, with a lived human experience. Human consciousness in other words. To me this technology is very clever but it's meaningl…

It's easy to generate believable backstory. A large LM comes to write the bio of the "artist" and even a few press interviews. If you like you can chat with it, and of course request art to specification. You can even keep it as a digital companion. So you can extend the realism of the game as much as you like.

Re: Stable Diffusion Public Release

#220

Post by swagmoney1606 »

andybak wrote: post #145
ChildOfChaos wrote: post #128

So what do I need to run this and how?

Anything close to a decent modern gaming PC will do it fine. I'm running on a laptop 3080 and I can generate 768x512 in about 20 seconds (with a 30 second overhead per batch)

No post body was provided.
Post reply on HN