Upgrade Hunyuanvideo to use the new diffusers format #582
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Outdated suggestions cannot be applied.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?
Update Hunyuanvideo to use the latest diffusers format.
Why?
As with Flux and PR #580, Hunyuanvideo also depends on old diffusers version. This PR is a follow up on issue #579 to remove the old diffusers version requirement.
How?
Hunyuanvideo doesn't have custom transformer or pipeline implementations, so the change is simpler. The attention processor also stays as-is, so the only change is to the
new_forwardmethod. Like with Flux, the example is now gated behind a minimum diffusers version.Parallelization support stays the same, i.e. only SP is supported.
Tests
Tested both with Ulysses/Ring:
https://github.com/user-attachments/assets/dd63eae4-3f88-4338-951e-851ad9e1ab6c
Other
PR #546 is also tested with these changes and works OOB.
Includes the changes made in #563 .