Conditional version of stylegan

[mrgloom]

What is the proper way to add condition to StyleGan? i.e. for example face landmarks. As I udnderstand one option is to encode face landmarks and concat embedding to random noise vector and pass it via adain, another option is to add encoder before fully convolutional network (replace constant input).

[rosinality]

I think there are many options, like methods you mentioned, but I don't know which will be best. I think concat condition embeddings to input of style MLPs will be most straightforward.