What does HackerNews think of stable-diffusion?

Leaked deck raises questions over Stability AI’s Series A pitch to investors | Apr 2023

The model was initially released in August 22, 2022, and everything from the GitHub organization that hosted the code, to the actual licenses being around and all the communication made it very clear that there was a bunch of groups involved with the model; Runway, CompVis, and Stability AI

Then Stability AI raised money from investors in October 2022.

Are you really telling me these investors didn't even do any sort of due diligence (not even "barely any" but literally any at all), didn't realized that Stable Diffusion was the work of many, and checked the license of the model and code?

That's a bit far fetched, to be honest.

Supposedly, this "leaked pitch deck" is supposed to show us that they lied to investors, but where is the pitch deck itself? Seemingly, only one of the slides is in the article, how could anyone reach any sort of conclusion based on just one slide?

Edit: The article seems to be some sort of clickbait trash that is so rampant around the web... One selected part:

> The Stable Diffusion code was released by researchers at LMU Munich in April 2022.

Links to https://arxiv.org/abs/2112.10752 which is the Version 2 of the paper, indeed released in April 2022. However, that paper is about, and links to https://github.com/CompVis/latent-diffusion which is not Stable Diffusion, it's Latent Diffusion. Stable Diffusion was released in August 2022, and is at https://github.com/CompVis/stable-diffusion

UK Has ‘No Chance in Hell’ of Making Its Own Tech Champs: ARM Founder | Sep 2022

Expand Context ↕

I had a look into that claim. The original work and most of the research heavy lifting seems to have been done at the LMU Munich. The main British participation appears to have been Stability AI lending computing power.

https://github.com/CompVis/stable-diffusion

DALL·E Now Available Without Waitlist | Sep 2022

Expand Context ↕

Official repo is straightforward: https://github.com/CompVis/stable-diffusion

Have to admit just started looking into it, mb there are better options

DALL·E Now Available Without Waitlist | Sep 2022

Expand Context ↕

Stable Diffusion is an AI model for computer generated art.

https://github.com/CompVis/stable-diffusion

DALL·E Now Available Without Waitlist | Sep 2022

Stable Diffusion is this: https://github.com/CompVis/stable-diffusion

It doesn't have a fancy product website because it's not really a product, it's 'just' the model. Developers can use it to build a product. The Stability.ai people themselves built one called Dream Studio (https://dreamstudio.ai), but there are also some free and open source frontends you can run on your own hardware if you have a GPU.

I guess your confusion comes from the fact that people tend to talk about "Stable diffusion" and not "Dream Studio" or one of the many frontends available for it.

From Deep Learning Foundations to Stable Diffusion | Sep 2022

Expand Context ↕

AFAIK Emad Mostaque is not (yet) an AI expert at all, he's a rich guy (former hedge fund manager) building a business that provides the funding for AI experts to do their thing. Stable diffusion itself was built by a team of academics [1], Emad is not a coauthor. Not to take away anything from what he's accomplished -- it's quite incredible -- but it doesn't mean he knows how to (learn to) build AI systems or do AI research himself.

[1] https://github.com/CompVis/stable-diffusion

Diffusion Bee: Stable Diffusion GUI App for M1 Mac | Sep 2022

Inertia, mostly. The official press release on August 10th linked to https://github.com/CompVis/stable-diffusion and diffusers didn't add support for Stable Diffusion until 5782e0393d on August 14th. There has been a ton of work on adding features on top of the CompVis Github release and backporting that work to Diffusers just isn't as interesting as adding new features to the existing fork. There has been some adoption of Diffusers though.

Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM | Sep 2022

In case anyone is confused by the clashing repos, here is how I was able to easily run this updated code.

Clone the original SD repo, which is what this code was built off of, and follow all the installation instructions:

https://github.com/CompVis/stable-diffusion

In that repo, replace the file ldm/modules/attention.py with this file:

https://raw.githubusercontent.com/neonsecret/stable-diffusio...

Now run a new prompt with a larger image. Note that the original model was trained on 512x512 and may lead to repetition especially if you try to increase both dimensions (this is mentioned in the SD readme) so just run with one dimension increased.

For example try the following example:

python scripts/txt2img.py --prompt "a person gardening, by claude monet" --ddim_steps 50 --seed 12000 --scale 9 --n_iter=1 --n_samples=1 --H=512 --W=1024 --skip_grid

I confirmed that if I run that command with the original attention.py, it fails due to lack of memory. With the new attention.py, it succeeds.

That said, this still uses 13GB of ram on my system.

I suppose you can check out the full repo with the updated code, which seems to have other changes, if you want to give that a try.

https://github.com/neonsecret/stable-diffusion/

I have already been using the original SD repo so I found benefit by just changing attention.py