Stable Diffusion

“Another one is AI doesn't take your job, AI takes the job of the previous AI. Claude took ChatGPT's job, right? Just like Midjourney, you know, took took Dali's job, took Stable Diffusion's job.”

“We use a number of things. We, at the time we used the chat to PT. We used the stable diffusion. I forget the first model we used. We used to do it. We used LORAS, which was we still do in some regards but LORAS is something that, you know, that you literally …”

“It only worked for, like, I think, like, certain ethnicities, like, because the model, like, say with Fusion was, like, trained, like, it wasn't trained on a very comprehensive data set. So maybe like only working on like white people. Right. And so like for e…”

“The main thing that really started driving all the traction was when stable diffusion came out. And a bunch of people came to us and like, Hey, actually, this looks kind of cool. Like you have GPU access. It's very easy to, you know, you have to think about, y…”

“So basically October, 20, 22, just like I hadn't written a line of PyTorch before that. So it's completely new.”

“That's the problem that that's the reason why stable diffusion actually became like popular, like, cause was because of the latent space.”

“We're gonna have the stable diffusion model for video generation soon. There are a lot of, like proprietary models in in video generation, but the first companies that are going to release an open source video Generation model. I think it is going to have a tr…”

“For that one, that was based on stable diffusion and we've since, like, iterated upon that a whole ton.”

“This is not just a wrapper off of like mid journey or stable diffusion. There's three parts to the tech. One is the actual model creation. The basis is stable diffusion, but we have our own algos on top of it for lighting aesthetics, demographics, posing.”

“There's one engineer, for example he fine-tuned a version of stable efficient with, like, his own Forty-Night-y incredible work, and he figured out things that no researcher had figured out at the time. Of course, we hired him.”

“And with the doctors one, the reality was that 39% of doctors in America are women, but in the stable diffusion results, it was only seven percent.”

“That's, like, you know, a year and a half in, like, we barely had any users or any revenue, and, like, we were, like, well, maybe we should look at, like, some use case, trying to think of use cases, and that was around the time, same, same time Stable Edition…”

“It's based on a technique that we developed while we were still at the university.”

“Open sourcing, like a foundation model as stable diffusion initially, that led to a whole lot of research on these models, which was, yeah, it was in, in retrospect, extremely important to do this. I think otherwise we wouldn't have seen the improvements we sa…”

“We showed that it's actually like helpful to incorporate like this implicit three D knowledge that Knowledge that is captured in all of the videos into the model, and then the model can learn much quicker than if you start from the pure image model.”

“The person that brought Laura's to stable diffusion actually works with us on, on some projects. His name is Simu”

“The original stable diffusion model supposedly was trained on like 600 K of GPU. Yeah. And these models cost in the millions to train, not tens of millions, at least initially.”

“Similarly, like, Stable Diffusion and Midjourney were all, like, pretty competitive with Dolly too, and actually probably making more money than Dolly too.”

“A lot of ML scientists, when they really build this stuff, the focus was more of like, always get it to work. It was never about getting it to work efficiently, or getting the code documented or organized.”

“We had hundreds of millions of images opt out of stable diffusion because we were the only company in the world To offer opt out of data sets.”

“So we train the whole internet and like stable diffusion is a 100,000 gigabytes in a two gigabyte file.”

“And the reproduction rate for something like stable diffusion is one percent.”

“We are working with multiple movie studios at the moment who are saving millions of dollars, just implementing stable diffusion by itself, let alone these other technologies.”

“With the additional breakthroughs that are coming through, it'll be 25 frame images a second. That's a hundred times speed up over a hundred times just from getting it out there and people interested in doing that.”

“Who's heard of stability, AI, and stable diffusion? That was trained using Lightning, right?”

“There was a thing in stable diffusion where every now and then you'd see like something that like a Getty image is watermark appear on the image.”

“You know, we're going, quickly going to go to a model in which you can run stable diffusion on the journey yourself on your computer or on your phone. That's like months or years away. It's not decades away. That's close.”

“Stable diffusion, I think some five billion and then like a smaller set of like twelve million for the what does nice look like fine tuning that's happened on the top and how they've optimized it.”

“Will I be able to tell the difference running Keynote and a web browser and email and Excel? No, I will not be able to tell. Would I be able to tell running Stable Dive Fusion? Oh, suddenly I get that image back in 10 seconds instead of 20 seconds. Oh no, that…”

“They are going to pay a hundred million dollars or more to Getty Images for stealing their content and allowing it to be republished In a commercial setting.”

“With Stable Diffusion or GPT-III, It can only know which ones are good by reference to the existing corpus, and it can make something new, but it doesn't, a new original, a new and original and striking, but it wouldn't know that it was good without the human …”

“First versions on top of the line graphics cards, on your own machine you can execute this, right, this open source. You could make an image in 15 seconds. I think we're down to three. And, like, with no hardware changes”

“He self-funded 600,000 and got these 20 engineers to come in and they created this thing that's like, you know, taken off and now, you know, valued over a billion dollars.”