Merged
Conversation
Perseus14
force-pushed
the
ltx2_audio_vae
branch
from
2e4af4c to
2aca047
Compare
mbohlool
requested changes
Mar 12, 2026
Perseus14
force-pushed
the
ltx2_audio_vae
branch
from
2aca047 to
c4e93ef
Compare
Collaborator
Author
|
@mbohlool PTAL |
mbohlool
approved these changes
Mar 12, 2026
mbohlool
requested changes
Mar 13, 2026
mbohlool
previously approved these changes
Mar 13, 2026
Collaborator
mbohlool
left a comment
mbohlool
left a comment
There was a problem hiding this comment.
Approving to unblock you after you added the license header.
Perseus14
force-pushed
the
ltx2_audio_vae
branch
from
c4e93ef to
861984e
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR introduces the
FlaxAutoencoderKLLTX2Audiomodel, providing a complete Flax/NNX implementation of the Audio VAE required for the LTX-2 pipeline. It supports encoding and decoding of audio spectrograms into latent representations, featuring fully configurable causal convolutions, dynamic spatial/temporal scaling, and strict parameter alignment for upstream checkpoint compatibility.