Repository navigation
[LTX-2] Add decode_audio to skip the audio decode in modular pipelines (tracking) - #9
Open
christopher5106 wants to merge 1 commit into
Open
christopher5106 wants to merge 1 commit into
christopher5106 wants to merge 1 commit into
Conversation
`LTX2AutoAudioDecoderStep` wraps `LTX2AudioDecoderStep` in a `ConditionalPipelineBlocks` that runs it unless `decode_audio=False`, in every LTX-2 and LTX-2.5 decoder chain. A video-only output (e.g. an IC-LoRA alpha matte) then skips the audio VAE and vocoder and gets `audio=None`; the video is unchanged, since the audio latents are still denoised jointly with it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Tracking PR for huggingface#15045, opened from this branch. Never merged here: once upstream merges it, this branch is deleted and the commit dropped from
scenariowhen it is rebased.pipe(..., decode_audio=False)skips the LTX-2 / LTX-2.5 audio VAE decode and vocoder and returnsaudio=None, for video-only outputs such as an IC-LoRA alpha matte. The video is unchanged. Details in the upstream PR and issue huggingface#15044.The same commit is cherry-picked on
scenario(56edff8a).