Skip to content

Conversation

@avjves
Copy link
Contributor

@avjves avjves commented Oct 28, 2025

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_forward method. 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 .

@avjves avjves changed the title Upgrade Hunyuanvideo to use new diffusers format Upgrade Hunyuanvideo to use the new diffusers format Oct 28, 2025
@jcaraban jcaraban self-assigned this Oct 28, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants