 Hello everybody, welcome back to another AI video. In this one, I want to talk to you about SDXL 1.0. That's right, Stable Diffusion XL has just launched and it is fantastic. And it has a lot of things going for it. First and foremost, it's open source, meaning it is free to use. In fact, you can use it a couple ways. First off, you can go to... And the link will be in the description below, but you can go to clipdrop.co right here. And you can see here that I can go ahead and start generating things as I see fit. Also take a look at my prompt. I'll talk about that in a second. So you can go to clipdrop and use it for free, unlimited. Also, if you have automatic 1111 or one of the other local installations on your Windows or Mac, you can use it on your computer. If you've got good enough hardware, you can run this for free and again, unlimited. This is all open source. So there's that. The second really interesting thing about this is that it's very friendly, so to speak. So you can create NSFW content if it's your thing, but if it's not your thing, you can do something like this. I can click on generate and I'll just click on it and continue in free mode because whatever. And you'll see here, there is a bit of a wait time behind it. But what happens is it will create the content and it will say NSFW on it. So there's the two workarounds. You can download it free and create NSFW, if that's your thing, or you can use the online version of NSFW, but do know that it is available. Now the SDXL model is in fact not one model, it is two models and it's trained with two things. Let me tell you a bit about that. So like I said, in regards to the model itself, it's not one model, but it's in practice two models. You run the base model and then it's followed by the refiner model. The base model sets the global composition, so it does all the heavy lifting and then the refiner model adds in the finer details. So in a sense, the SDXL 1.0 is a base model of 3.5 billion parameters, and yes, that's with a B. And then it has a model ensemble pipeline of 6.6 billion parameters. So that's the refiner model. Pretty darn good, the refiner model also basically improves the output by enhancing color accuracy, increasing the contrast, and adding in, again, the finer details. So it kind of does it in two passes. Now, if you want to install this model locally, I'm going to put a link in the description below. And it has a walkthrough on how to do that. But if you want to use it for free on clip drop, I will also put a link to that as well. You can just start making content right now if you wanted to. And then in a second, in a few minutes, I'm going to create another video showing the difference between something like Mid Journey, which you pay for, and SDXL 1.0, which is free. We're going to do a comparison. So that's coming up next. Anyways, thanks for watching this video. Be back soon.