fix(minimax-h3): align Ref2VA audio and conditioning paths - #81
Merged
Conversation
- read prompt files before generation when no inline prompt is supplied - encode MiniMax-H3 reference audio per stereo channel and resample standalone audio consistently - build Ref2VA presentation as ordered reference segments for image/video/audio inputs - share condition noise RNG across reference latents and add debug dumps for alignment checks - enforce a minimum MiniMax-H3 generation canvas to avoid invalid tiny outputs - document MiniMax-H3 output resolution constraints
Remove temporary tensor-load/dump and Qwen debug-target plumbing that was accidentally included with the Ref2VA fixes. Keep the functional audio, conditioning, prompt-file, and resolution changes intact.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.