LDSR improvements - cache / optimization / opt_channelslast #5586
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Outdated suggestions cannot be applied.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 PR aims to improve the LDSR through the following means.
Ability to cache the LDSR model (as an option in the Settings tab) - Good if you use LDSR to upscale often and have the RAM to store it. You won't need to reload the model every time you upscale.
Apply optimization (such as Xformers) - This uses the
sd_hijacklogic to apply optimization to the LDSR model the same way it does to all the SD models. This may help lower-end machines.Allow Channels Last memory format - The
--opt_channelslastnow affects the LDSR model as well and may improve performance.Device agnostic - It should now allow CPU operation as well