The Man behind Stable Diffusion

I really enjoyed this interview [1] with Emad Mostaque who I gather is probably the key funding and organization player in that stuff. It remains to be seen exactly how "open" it winds up playing out over time, but they're talking a compelling game and the EleutherAI people seem to be pretty heavily involved, which you probably wouldn't do if you weren't serious. Yandex has also put up a ~100B language model [2]. My old colleagues at Meta have also started nibbling around the edges of opening some of this stuff up [3]. The Meta folks still aren't just handing out the big ones, but they're definitely moving the ball forward. In particular their release of the training logs is a really positive development IMHO as it opens the curtains a bit on the reality of training these things: it's a difficult, error/failure-prone process, there's a lot of trial-and-error, restarting from checkpoints, etc. Anything that puts downward pressure on the magical thinking is A-OK in my book. The reality of this stuff is exciting/impressive enough: there's no need to embellish or exaggerate. [1] [VIDEO] [2] [LINK] [3] [LINK]

The guy's name is Emad Mostaque btw There's a recent video interview he did that goes into his vision: [VIDEO]

Stable diffusion is good open source software and is well motivated in a very complicated technology/political space. Sure they inherit all of the existing problems with image datasets but they have some plans to mitigate racial and socio-political bias. The alternative is to either not do the project or make it secretive under the supposed motivation of safety. This interview is a good overview of the principles behind their approach: [VIDEO]

Yep, here’s interview with the founder of Stable AI, which includes their intent to release Stable Diffusion and be more open than OpenAI: [VIDEO]

Interview 7mo ago w/CEO of StabilityAI. [VIDEO] Not too surprised about funding issues from the casual answer. I’m not saying it was bad to self fund a project, but having to choosing between your life and fun (and potentially very profitable) projects is not easy.

>> “The safety checker: Following the model authors' guidelines and code, the Stable Diffusion inference results will now be filtered to exclude NSFW content. Any images classified as NSFW will be returned as blank. To check if the safety module is triggered programmaticaly, check the nsfw_content_detected flag like so: Potential NSFW content was detected in one or more images. Try again with a different prompt and/or seed." — That’s disappointing and appears conflict my understanding of Stability.AI’s founder claim that limits like these would not be injected into the code; this based on an interview he did here: [VIDEO] If I am correct, makes me question all the other claims he made, which is unfortunate. ___ Edit — Here is a direct link to point in the interview I was referring to above: [VIDEO]

Y/ou can't comment unless you pay to subscribe.. lol - isn't that a company blog post? Anyways.. this shit grinds me.. yet another "open source" AI proejct pretending to be fo rthe people.. finally get a massive valuation and now it's all "we must be security concious".. Hypocrtyes and here is an interview with the founder of Stable Diffusion stating the exact opposite approach by "having faith in people"! [VIDEO]