Flux: Fix random validation errors due to some tensors being on the cpu #629
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
|
thanks! |
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Outdated suggestions cannot be applied.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.
Flux had random validation errors similar to SD3 in issue #546. This pull request makes sure all tensors are moved to the GPU before calling the transformer. Code is mostly copied from helpers/sd3/pipeline.py. In the case of Flux, the transformer also takes in
txt_idsandimg_idsparameters which also needed to be moved to GPU.I did some testing with extra debug prints and the validation image was successfully generated even when tensors were originally on the CPU.