 Important note about mid-journey negative prompting, or in other words, telling mid-journey what you don't want in the image is this. The more clear you are about what you do want in the image, the less you need to tell mid-journey what you don't want. And if you don't do a good job of telling mid-journey what you do want and only give a bunch of things you don't want, the image turns out to be quite weird. The reason is because when you tell mid-journey what you don't want, what is it doing? It's taking those words, those key words of what you don't want, and looking at its own database and disregarding all of the images in the database that have those words as key words or tags of those images. So you're basically disregarding possibly millions of images to be considered in the creation of your image, which then makes mid-journey have a very small database and it may come up really weird. So let me go ahead and show you on the screen what I mean. As I said in the other video above, I was trying to play around with what if I can create a beach. I just tell mid-journey beach, but I don't want sand or water or da, da, da, da. Okay, so let me show you what happens when I do that. I'm going to go and share my screen right now. All right, so what you can see on the screen is when I said I just want a beach. This is what I do want, right? What I do want. That's all I said. Just a beach. But then this is the negative prompt, right? Remember, you can add in various ideas. It could even be multiple. It doesn't even just be one word. It could be two words, three words or whatever. But then you separate additional things you don't want with commas, right? I don't want all of these things. You know, definitely don't want them negative .999. And look what it comes out as. I'll just show you. I'll just look kind of look more closely here. What is that? I don't understand why these three things have to do with beach. My guess is that maybe mid-journey given that I disregarded so many things. It's pulling from certain modern works of art. Maybe art works that somehow have the beach, the keyword beach, a tag to it in some weird way. Maybe it's maybe the artist's name is beach or whatever. I don't know. And this is the only one that's hinting at a beach. It looks like a beach without, guess what, without any sand, red, it does have blue, right? This is kind of gray, blueish. Didn't do a great job there, but it was doing its very best. I also tried it again over here without commas. Just sand, red, blue, cows, beach, buildings. It didn't do as good of a job because you could see blue here, blue here. Again, these are not beaches, but maybe some kind of artists or some other collection with tag with the word beach in it for some reason. So not a good idea. All right, well, how do you do it right? As I said, if you add in more of what you want, describe that more clearly. And then, so I want to thank Mara and Gregory, you know, Gregory, Vahanian and Mara kind of collaborated on this idea together. So this is the prompt. California, gravel, beach, sunset. That's four words instead of my one word of just beach, right? So it's pulling from much more of the database because it's got four words and then the no sand. Remember, the negative prompt can either be the fancy way that I do it, which is, you know, double, sorry, double colon at the end with negative 0.999 or it can simply be dash, dash, no, and then whatever, whatever you don't want separated by commas. The only drawback of that dash, dash, no, is that it's essentially a negative 0.5. So it only decreases the possibility of it by 50%, whereas I'm decreasing the possibility here by 99.9%. But however, like I said, if you describe what you want really well, okay, or better, then it will do its, then it will do a pretty good job of taking out what you don't want, even just with the no command instead of the fancy way that I do it. There's a little bit of sand here, but it's mostly beachless sand, right? So good job on on doing this, Mara and Gregory, and I hope this is helpful for everybody watching this. Thanks.