Open edward3862 opened 11 months ago
You are right, the images should contain similar content. Unfortunately, the CLIP feature estimation is very sensitive to hyperparameter setting. I would try increasing the number of optimization steps (conditioning_optimization.opt_iters) in parameter_estimation.yaml.
Hello,
What is the number of "opt_iters" used to obtain the results shown in the teaser of the article?
Thanks!
Hello, I'm running the provided script for CLIP feature estimation. When I regenerate the images by setting
regenerate_tokens
, I get the following results intoken_regeneration_with_ref.png
.I'm not sure whether this meant to be correct. In my understanding, the regenerated images are supposed to contain similar content with the input image. Is there anything I missed and how should I fix this issue?
Thanks!