[adamj9431]

How is Stable Diffusion on DreamStudio.ai so much faster than the reports here? Seems to only take 5-10 seconds to generate an image with the default settings.

I.e. How are they providing access to GPU compute several orders of magnitude more powerful than an M1, for free?

[fleddr]

The guy behind it is an ex hedge fund manager. Using private funds he's built a massive fleet of A1000s at AWS.

So it's an enormous amount of compute created from private funds that he considers to be "for humanity". Currently, he funds it and is also the "GPU overlord", he exclusively decides which applications gets to use it.

His plan, or at least his claim, is to transform this situation in it being more diversely funded (institutions, businesses, even the UN) and for access to be decided by committee with main criteria it being useful for humanity.

Let's see if he sticks to his word, but I find it inspirational. AI was on a trajectory to be solely in the hands of a hand full of ultra rich companies that can afford to train and run it, and us poor mortals being at the whims of gatekeeper terms.

This guy is on a trajectory to put AI in the hands of the people. Not just for art, for everything. If he fully sees this through, he's destined to be a tech icon.

[preommr]

The guy's name is Emad Mostaque btw

There's a recent video interview he did that goes into his vision: https://www.youtube.com/watch?v=YQ2QtKcK2dA

[schleck8]

1. Dreamstudio is paid, with 2 EUR worth of credit for free.

2. The M1 GPU is an iGPU. A good iGPU, sure, but it's not anywhere near the performance of a dedicated, cooled GPU with dedicated VRAM.

On a 2060 Super with 8 GB of VRAM and with tensor cores it takes 15 seconds to infer with the default settings. If Dreamstudio uses deep learning GPUs then there is your answer to why it is as fast.

[tgtweak]

A100 devices in the cloud on preemptive/spot instances?