What AI generated video is exactly?

I was wondering what AI video is exactly and how does it work. I'm aware it sounds silly at first, but from development standpoint, I can't grasp my head around it.

Let's imagine I have a prompt "man is jogging in a beach";

What does AI video generator do exactly?

If video is just a sequence of images in time, does the AI first generate first image at random and uses that image as a reference for the next image …

ai generated ai video artificial development generated generator head imagine prompt video work