Fix vae_encodings_fn hash in train_text_to_image_sdxl.py #7171
Conversation
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
Merged
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
sayakpaul
approved these changes
Mar 1, 2024
Member
sayakpaul
left a comment
sayakpaul
left a comment
There was a problem hiding this comment.
This is a single instance of such behaviour. Thank you!
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Outdated suggestions cannot be applied.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.
The hash used as new fingerprint when computing the VAE encodings in train_text_to_image_sdxl.py should change if the VAE changes.
Previously if someone used different VAEs using this script, it would always reload the first result in the dataset cache instead of recomputing using the different VAE.
I haven't checked in other examples for similar cases, maybe it can be worth checking.
@sayakpaul