 Hello, everybody. Welcome back to another Leonardo.ai tutorial. In this one, I'm going to show you how to create your own model, your own AI text to prompt art generator model, your own image generator model, basically your own creative model for image and art generation using Leonardo.ai. As far as I know, Leonardo.ai is the only tool that allows this, the only app that does it, and I'm going to show you how to do it step by step. So when you log in, you'll see all of these things here. You'll see the start. These are the pre-built models, and they're fantastic, by the way. But what I want to do is I want to show you how to create your own. So here you go. On the left side, you want to go down to training and datasets and fine-tuned models. Let me go to fine-tune models first, and this way I can show you. So when I clicked on fine-tune models, these are the models the platform gives you to use. These are models created by the community that you can go ahead and use even though it's slowly loading. And then here's the one we're looking for, your models. And you'll see here that I have created one called Caravaggio, and I've built this model on images that I took and I did it based off of this reference sheet here. So I really like Caravaggio's style. So I took about 10 or 12 different... I took 12 actual generated images in his style and then I created a model. How did I create this unique model? Simple. I go to training and datasets. When you click on this, you'll get a couple options. What you want to do is you want to click on new dataset. I'm going to click on this and then I'm going to give it a name. And this one, I'm going to call it Pixar2 because I've got a Pixar version one. And I just want to show you the technique. So I'm just going to call it Pixar2 and I'm going to quickly name it. The most important part here is selecting the images and dropping them in. Now, I will show you before I drop my own images in, you can take images from your own personal feed and you can also take images from the gallery search. So if you're looking, if you like someone else's stuff, like this Japanese styles type thing, you can use those images as part of your dataset. For me, I've got 12 images. If I go to my pictures folder here, I've got 12 Pixar, cute Pixar style images that I'm going to use. I'm just going to grab them, drag and drop them. Do note that you need a minimum of eight images in order to go ahead and create a dataset. So if you only got like a couple, it won't work. So I took these 12 of them and I think they're nice and cute and they're Pixar-y and they're fluffy and they get across the style that I want. All you need to do now is click on train model and here's what happens. You go ahead and just type it in. So I'm just going to type in Pixar too. You can type this in a little bit more specifically, but I just want to quickly show you how this works. Instance prompt, these really don't matter too much if I'm being honest. And then I'm going to go and click on start training. When you do that, oh, you've submitted your maximum pending models. Okay, so I've got a couple of in the queue. So I'm going to click out of that, but in order for you to do this, all you got to do is click on start training. I'll click back out and then once it's done and it takes a couple of minutes, you then want to move over to fine-tuned models. And you'll see here that I've got Caravaggio, which is one that I've already made and I've got the Pixar one being created right now, but it's going to take a few more minutes to finish. So let me show you how to use your own model. So what I would do is you will have your own models here. I'm going to use this one here. I'm going to click on, well, let's click on settings first and it just tells you the name of it and some basic descriptions, nothing too important. Click on view, here's where it gets good. You see here, this is an example of a low res image that I built using it. And if you know Caravaggio, he uses lots of dark shadows and it's pretty damn good. Not going to lie. So I'm going to go ahead now and click on generate. And then here's where the magic happens. I can now just select this in my fine-tuned models. I've got Caravaggio selected. I can go ahead and then just start creating stuff. So what I'll do is I'll just create dogs reading a book. I'll click, I'll make two of them. Now let's click four at a time. I'll use the default steps here. You guys can go through this as you can see fit. And then I'm just going to click generate. And now instead of typing in, you know, dogs reading a book, comma, in the style of Caravaggio, comma, shadows, comma, photo realistic, comma, et cetera, et cetera, et cetera. You just got to type in the basics and then it knows what you like because it basically sees it. So here we go. We've got dogs reading a book and you know what? It's done a pretty damn good job. This one here over here, this is like a old school Caravaggio painting. What I would do next is I would either download it if I like it as is or you could upscale it right here so I can make it nice and fancy and add in some details. But that's how you train a model and create your own model inside Leonardo.ai. Thanks for watching.