Note on StyleGAN 1 and 2

Adaptive Instance Normalization

Actually BigGAN has some similar design with this.

StyleBlock

Mapping Network

Mapping Network warp the input Normal distribution into a more complex manifold. Both ease sampling with a Gaussian distribution and facilitate complex distribution as input.

Truncation Trick

Truncation trick has been used in BigGAN in latent space directly, here they use truncation trick in $w$ space instead of $z$ space.