How do they ensure the same looking person is generated each time?

You can generate consistent faces simply by using random non-existent names. Wich in turn you can use to train a custom LORA with Dreambooth (needs about 20 images) or use ROOP (a single one can be enough). And of course you can just mix and match it as you please, mix multiple real faces together into a new one, use dedicated face generators like thispersondoesnotexist.com and so on.

This barely even takes effort anymore, e.g. quick ROOP FaceSwap with the photo from the article.