Improve performance of fast test by reducing down blocks #5290
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
Contributor
Author
|
@sayakpaul can I add you as a reviewer? |
tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl.py
Outdated
Show resolved
Hide resolved
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
…#5290) * Reduce number of down block channels * Remove debug code * Set new excepted image slice values for sdxl euler test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #5260 by reducing the channels of the downblocks of the UNet model.
So far all tests pass on my local machine without any changes, except for
test_stable_diffusion_xl_euler. The deviation for image slice check is bigger than 0.01, which is why I changed the assert to 0.1. Are we ok with this?According to
timethe running the tests without the optimizations took 2:13.44, with it only took 1:04.99 total, so the speed up seems worth it.Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.