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] [this video] [2] [link] [3] [link]

>> “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: [this 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: [this video]