Skip to content

fix: remove normalization of audio in LTX Mel spectrogram creation #11990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
comfyanonymous merged 1 commit into from
Jan 20, 2026
Merged

fix: remove normalization of audio in LTX Mel spectrogram creation #11990

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 0 additions & 10 deletions comfy/ldm/lightricks/vae/audio_vae.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,20 +103,10 @@ def resample(self, waveform: torch.Tensor, source_rate: int) -> torch.Tensor:
return waveform
return torchaudio.functional.resample(waveform, source_rate, self.target_sample_rate)

@staticmethod
def normalize_amplitude(
waveform: torch.Tensor, max_amplitude: float = 0.5, eps: float = 1e-5
) -> torch.Tensor:
waveform = waveform - waveform.mean(dim=2, keepdim=True)
peak = torch.max(torch.abs(waveform)) + eps
scale = peak.clamp(max=max_amplitude) / peak
return waveform * scale

def waveform_to_mel(
self, waveform: torch.Tensor, waveform_sample_rate: int, device
) -> torch.Tensor:
waveform = self.resample(waveform, waveform_sample_rate)
waveform = self.normalize_amplitude(waveform)

mel_transform = torchaudio.transforms.MelSpectrogram(
sample_rate=self.target_sample_rate,
Expand Down