I was coming up with a series of images for a story that I'm working on, and I kept running into a problem.

It turns out that this issue is pretty common among those who try to use artificial intelligence generators to make images.

Once you get the hang of it, it's pretty simple though.

But no matter how good you get at it, you keep running into the same thing.

When your image comes up with a character,

a specific person that you want to appear again, it's pretty difficult to get them to show up,

just like that in other images. For example, let's say you're trying to come up with a short

story of a man who finds a cabin in the woods. He steps inside and encounters a ghost so he

decides to run away.

This man would start coming up looking differently in the rest of the images.

In some, he might have long hair.

In others, he might be wearing something different.

Maybe a different face, different style of drawing or illustration,

maybe even a different background. But anyway, some artists started

to take advantage of this as a new form of expression, asking AI what it looks like, and then

have it give you an image of itself, the AI machine or whatever. And it's such an interesting

idea, right? But there was a new thing that I learned about. There's this technique called

negative prompt weights. And basically, all you have to do is tell the AI to make images that are

opposite of a prompt. Like, if you tell it something like, give me an image of heaven. It might

give you hell. Well, that's what we were hoping for at least. But this ended up getting much,

much more complicated. You see, it isn't just analyzing visuals, but concepts. Things that

aren't exactly the opposite as you and I perceive them to be, but yet they're opposite conceptually.

...