 Hello everybody, welcome back to another mid-journey tutorial. In this one, I want to show you a couple things. One, I want to show you how to reverse engineer the prompt for any image, not the image specifically but for any style. So if you upload a photo and you want something in the same style, I'm going to show you how to reverse engineer that and it also works for like art. So if you've got like a cartoon or a character that you want to reverse engineer, how do they come up with that? I'm going to show you how to do it. And the way to do it now is with a new feature that just launched in mid-journey and I'm going to show you it. So what it's called is it's called Describe, so you do forward slash describe and then hit enter. When you do that, you can drag and drop a file, an image of some sort, and then it's going to describe it for you. So for this example, I'm going to use this one. This is a very famous image that was taken at the end of World War II. I believe it was in Times Square, Alfred Eisenstadt, and it's just one of the most iconic images of the 20th century. This is it. But what I did is when I hit forward slash describe and hit enter, here's what you get. You have one here. You see that it has one, two, three, and four. What it basically done is it's given us four cracks at the type of prompt that could be used to create an image like that. Very, very similar. Now, some are better than others. I'm not going to lie. What I'm going to do is I'm going to click on one, two, and three. So I'm going to click one, and then I'm going to go ahead and click submit. You'll notice here that when I do this, there is an imagine this box. Normally, you would see a remix box, but now it's called imagine this for this one. So it's kind of cool. I'm going to hit one, two, and three, so it's going to pop those images out pretty quickly here. And then when I click on four, do note that in the imagine this box, you can actually go ahead and make changes. So if there's something in here that you don't want, like, for example, Mono Ha, I don't know what that is. So if I wanted to, I could delete it just like I did there. I can also add things in. So Argus C3, I don't know what that is. But if I wanted to add in, for example, black and white, I would do that. I can delete this aspect ratio, which is a little strange to me. These are all things you can do inside the imagine this box here. So I'm going to run all four of those. And when they're done, I'm going to come back and I'm going to show you one last step. All right, welcome back. So it's generated all four sets here. So let's take a quick look here. If I click on this one, this one is very modern. It has a 2020 or a 19, between 1990 and like 2020. So it's a modern type style. So I would discount this one and also looking at the prompt here. Photo, photo, photo, photo, photo. It's a little dodgy. So that one didn't quite work out. This one here also very, very good. However, it's in color. So if I wanted to remix this, and I loved, let's say, I really like this bottom left one. I like the third one and the fourth one. They're really good. Here's what you could do. You can click on V3, for example. And now, instead of the imagine this, we get the remix prompt. So instead of a sailor and a woman kissing the street, we could have all of this and then I would say, uniformly staged image is black and white, comma. And then I would go ahead and hit submit and it will do it in black and white. Other thing here, you'll see here that here's another four. These are really good. This is really good stuff. I could just hit, you know, U4, U3, and then just keep them. And here's the other option. This is also excellent. It kind of recreates the idea, oh, this guy's hand is traveling. I think that's a penalty in basketball. But there you go, guys. This is how you do it. This is how you reverse engineer prompts and you can already see here that it's already getting the black and white treatment here. So this one here, for example, I added in black and white and it took out some of that coloring. So that's it. That's how you reverse engineer prompts. That's how you figure out the prompt for any image. Thanks for watching.