EVA3D icon indicating copy to clipboard operation
EVA3D copied to clipboard

Published 20 hours ago • verified publisher icon hongfz16

About PTI Inversion

Open qplwme opened this issue 1 year ago • 1 comments

Hi! Thanks for your great work. I'm trying to inverse target images as you descibe in 4.5 Inversion section. Could you give me some clue about it?

In detail, I've got an embed with shape(1, 18, 512) at (PTI repo)/embeddings/barcelona/PTI by following https://github.com/danielroich/PTI. However, I just dont know how to change the embed to fit your 'mean_latent' in line 269 generation_demo.py

qplwme avatar May 08 '23 03:05 qplwme

Hi. Thank you for the question.

Actually, the 'mean_latent' is used for truncation. And you do not need to do truncation in inversion. So you can just pass None to 'mean_latent'.

hongfz16 avatar Jun 17 '23 08:06 hongfz16