Style mixing video and update projection code#17
Open
PDillis wants to merge 5 commits intodvschultz:mainfrom
Open
Style mixing video and update projection code#17PDillis wants to merge 5 commits intodvschultz:mainfrom
PDillis wants to merge 5 commits intodvschultz:mainfrom
Conversation
Owner
|
Sorry it looks like I added some content to the generate script which is causing merge conflicts. I’ll try to look at this more this week. appreciate you cleaning up my garbage code :) |
Author
|
No problem, I was going to fix the merge conflicts myself but then I figured you were toying with other things as well (also my PC died on me). Let me know if you want any help as well, but the code isn't garbage haha, as I said, it's not a priority to 'fix' it. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
style_mixing.py: Added the style-mixing video option using lerp; it helps to play with this, as the--col-stylesreally gives you the power to control what is transferred and what isn't.projector.py: Added an option for the projector to set the number of steps as well as to save every step (both the image and dlatent.npy will be saved); I used this for generating a specific latent walk in my models by getting these dlatents and moving through them in a controlled manner, so I hope it's useful for someone else. The next step is to take a dir of images to project, but I'll do that next year.generate.py: Minor fixes to code style as well as a bit of optimization; more can be done here, but not a priority.