[exit]

take a look at "Figure 8" from the original paper:

https://imgur.com/a/rZsWzDa

we can smoothly interpolate between faces, so it seems impossible to me that these are just memorised from the training set

[misterdoubt]

I just realized that the eyes, nose, and mouth are always in the same place in these images... even though the head might rotate around them.

[gwern]

That might be because they cleaned the dataset thoroughly. I vaguely recall there was something about 'facial landmarks' and alignment in the ProGAN work which was presumably carried over to StyleGAN. Doubtless helps the final quality.

However, aligned faces are definitely not required - I didn't do any kind of alignment for my anime faces and you can see the eyes/nose/mouth in all sorts of positions in the samples & videos.