danielroich / PTI

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Run PTI on 256*256 images

hyungkwonko opened this issue · comments

Dear Daniel,
Thank you very much for the great work.
I am trying to apply PTI on my trained model which has 256 * 256 resolution.
Could you give me any tips on which part should I fix in the code?
Many thanks,

Sorry, I found it by myself.
Closing this issue.

Sorry, I found it by myself. Closing this issue.

Hi, can you share where can I fix the code? I want to apply it to a 128*128 model. Thank you!

I am so sorry that it is too late to answer your question.
I found this as another person asked the same question with the link to here.

To answer your question, it is a bit long to explain how to use pretrained model with different dimension, you may want to refer to my implementation.
Specifically, you may want to refer to w_projector.py which is an example for 256 dimension. You can apply this for your 128 dim model
Please read the code and reach me out if you have any more questions.