ZPdesu/II2S

Some questions about II2S

johannwyh opened this issue · 2 comments

johannwyh commented

First of all, thank you for presenting this marvelous work.

I have some questions to consult that,

  1. Does your inverted embedding belong to W+ space? In another word, can the saved latent code be directly used as the input of a StyleGAN2 model?
  2. How many iterations does it take to generate a roughly accurate reconstruction result? As 1300 iterations on 1024 resolution is sometimes too slow.
  3. Is it possible to embed a batch of images at the same time?

Thank you very much!

ZPdesu commented
  1. Yes.
  2. 800 iterations are actually enough.
  3. Not implemented yet... but I think it is doable.

Also, please check the updated code.

jfemiani commented

Good questions, seem to be answered. I do not think this is a feature request for (3) so I will close this.