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

Stable Diffusion 2.0

stability.ai

Post reply on HN
Print view View original

191–200 of 519 posts

Re: Stable Diffusion 2.0

#191

Post by stymaar »

prakhar897 wrote: post #172
LASR wrote: post #27

I am a solo dev working on a creative content creation app to leverage the latest developments in AI. Demoing even the v1 of stable diffusion to the non-technical general users blows them away completely. Now that v2 is here, it’s clear we’re not able to keep pace in developing products to take advantage of it. The general public still is blown away by autosuggest in mobile OS keyboards. Very few really know how far…

I'm in a kind of same boat. I think indie games are the way to show true potential of SD. Hence, I'm working on http://diffudle.com/ which is a mix of Wheel Of Fortune + Stable Diffusion + Wordle. I Can't figure it out but feels to me like its lacking something.

> Hence, I'm working on http://diffudle.com/ which is a mix of Wheel Of Fortune + Stable Diffusion + Wordle. I Can't figure it out but feels to me like its lacking something.

That's awesome, I love it!

Re: Stable Diffusion 2.0

#192

Post by xkapastel »

charcircuit wrote: post #127
xkapastel wrote: post #111

Earlier quoted context omitted.

Why do you think it is not open source? The model weights, model architecture, and dataset are all available.

Read the license of the model: https://github.com/Stability-AI/stablediffusion/blob/main/LI... 5. and 7. make it not open source

I don't see how it contradicts the open source definition at https://opensource.org/osd, could you point it out for me?

Re: Stable Diffusion 2.0

#193

Post by stymaar »

ericd wrote: post #165
LASR wrote: post #120

Earlier quoted context omitted.

It started as an AI-powered MS paint for my son. But after demoing it to a few coworkers, it morphed into a bit more than that. Now it’s more of a storybook creator that young kids can use to generate their own stories. Not looking to monetize at all. But inference is expensive. So might have something to cover costs. Some backstory: When I was growing up in the early 90s, my dad took me into his office over the week…

I have some young kids, would love to try this out with them if you’re sharing.

Same here! (And I also remember playing with MS paint on my dad's work computer)

Re: Stable Diffusion 2.0

#195

Post by josephcsible »

xkapastel wrote: post #192
charcircuit wrote: post #127

Earlier quoted context omitted.

Read the license of the model: https://github.com/Stability-AI/stablediffusion/blob/main/LI... 5. and 7. make it not open source

I don't see how it contradicts the open source definition at https://opensource.org/osd , could you point it out for me?

For the most blatant violation, look at point 6 of the OSD and attachment A of the license.

Re: Stable Diffusion 2.0

#196

Post by imran_khan »

To put things in perspective, the dataset it's trained on is ~240TB and Stability has over ~4000 Nvidia A100 (which is much faster than a 1080ti). Without those ingredients, you're highly unlikely to get a model that's worth using (it'll produce mostly useless outputs).

That argument also makes little sense when you consider that the model is a couple gigabytes itself, it can't memorize 240TB of data, so it "learned".

But if you want to create custom versions of SD, you can always try out dreambooth: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion, that one is actually feasible without spending millions of dollars on GPUs.

Re: Stable Diffusion 2.0

#197

Post by imran_khan »

trained on is ~240TB and Stability has over ~4000 Nvidia A100 (which is much faster than a 1080ti). Without those ingredients, you're highly unlikely to get a model that's worth using (it'll produce mostly useless outputs).

That argument also makes little sense when you consider that the model is a couple gigabytes itself, it can't memorize 240TB of data, so it "learned".

But if you want to create custom versions of SD, you can always try out dreambooth: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion, that one is actually feasible without spending millions of dollars on GPUs.

Re: Stable Diffusion 2.0

#198

Post by imran-khan »

To put things in perspective, the dataset it's trained on is ~240TB and Stability has over ~4000 Nvidia A100 (which is much faster than a 1080ti). Without those ingredients, you're highly unlikely to get a model that's worth using (it'll produce mostly useless outputs).

That argument also makes little sense when you consider that the model is a couple gigabytes itself, it can't memorize 240TB of data, so it "learned".

But if you want to create custom versions of SD, you can always try out dreambooth: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion, that one is actually feasible without spending millions of dollars on GPUs.

Re: Stable Diffusion 2.0

#199

Post by NKosmatos »

Wow, just wow!

Newbie question, why can’t someone just take a pre-trained model/network with all the settings/weights/whatever and run it on a different configuration (at a heavily reduced speed)?

Isn’t it like a Blender/3D studio/Autocad file, where you can take the original 3D model and then render it using your own hardware? With my single GOU it will take days to raytrace a big scene, whereas someone with multiple higher speced GPUs will need a few minutes.

Re: Stable Diffusion 2.0

#200

Post by smcleod »

minimaxir wrote: post #5
gst wrote: post #4

Earlier quoted context omitted.

> Doing a 2.0 release on a (US) 2-day holiday weekend is an interesting move. Their HQ seems to be located in London.

True, but it's going to dampen the launch a bit.

I don't see why? The world is a whole lot bigger than the USA!
Post reply on HN