Improve speed of applying TI embeddings #5422
Merged
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
…s to accomodate new TI embeddings. This saves time.
RyanJDick
requested review from
damian0815,
lstein,
blessedcoolant,
GreggHelt2,
StAlKeR7779,
brandonrising and
hipsterusername
as code owners
hipsterusername
approved these changes
Jan 5, 2024
|
The man the myth the legend. |
|
I'm unable to see any difference on my end with either SDXL or SD1.5 |
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Outdated suggestions cannot be applied.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.
What type of PR is this? (check all applicable)
Have you discussed this change with the InvokeAI team?
Have you updated all relevant documentation?
Description
This change saves time when applying TI embeddings by skipping unnecessary weight initialization steps. (See inline source comment for more details.)
QA Instructions, Screenshots, Recordings
In my local testing with SDXL, this reduced
sdxl_compel_promptfrom ~8s to ~0.8s.I confirmed that there was no change to the images produced with a fixed seed after the fix.
Added/updated tests?