Fix TAESD preview to only decode first latent, instead of all #1863
Conversation
This file contains 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Outdated suggestions cannot be applied.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.
The TAESD preview returns the first latent anyway to be displayed, but the code before performed decoding on all latents and returned the first index. For single images that is fine, but 1) causes slowdowns when using batches greater than one, and 2) causes VRAM OOM when batch size is a fairly large number.
Changed code now passes only the first latent into the decoder, in the form [1, :, :, :] via slicing, and then stores result into x_sample as [channels, h, w] same as before. No more VRAM isssues with large batch sizes, and preview is faster for any batch size > 1.