Skip to content

Remove useless code. #10223

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
Oct 5, 2025
Merged

Remove useless code. #10223

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
11 changes: 0 additions & 11 deletions comfy/ldm/ace/vae/music_dcae_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,6 @@ def __init__(self, source_sample_rate=None, dcae_config={}, vocoder_config={}):
else:
self.source_sample_rate = source_sample_rate

# self.resampler = torchaudio.transforms.Resample(source_sample_rate, 44100)

self.transform = transforms.Compose([
transforms.Normalize(0.5, 0.5),
])
Expand All @@ -37,10 +35,6 @@ def __init__(self, source_sample_rate=None, dcae_config={}, vocoder_config={}):
self.scale_factor = 0.1786
self.shift_factor = -1.9091

def load_audio(self, audio_path):
audio, sr = torchaudio.load(audio_path)
return audio, sr

def forward_mel(self, audios):
mels = []
for i in range(len(audios)):
Expand Down Expand Up @@ -73,10 +67,8 @@ def encode(self, audios, audio_lengths=None, sr=None):
latent = self.dcae.encoder(mel.unsqueeze(0))
latents.append(latent)
latents = torch.cat(latents, dim=0)
# latent_lengths = (audio_lengths / sr * 44100 / 512 / self.time_dimention_multiple).long()
latents = (latents - self.shift_factor) * self.scale_factor
return latents
# return latents, latent_lengths

@torch.no_grad()
def decode(self, latents, audio_lengths=None, sr=None):
Expand All @@ -91,17 +83,14 @@ def decode(self, latents, audio_lengths=None, sr=None):
wav = self.vocoder.decode(mels[0]).squeeze(1)

if sr is not None:
# resampler = torchaudio.transforms.Resample(44100, sr).to(latents.device).to(latents.dtype)
wav = torchaudio.functional.resample(wav, 44100, sr)
# wav = resampler(wav)
else:
sr = 44100
pred_wavs.append(wav)

if audio_lengths is not None:
pred_wavs = [wav[:, :length].cpu() for wav, length in zip(pred_wavs, audio_lengths)]
return torch.stack(pred_wavs)
# return sr, pred_wavs

def forward(self, audios, audio_lengths=None, sr=None):
latents, latent_lengths = self.encode(audios=audios, audio_lengths=audio_lengths, sr=sr)
Expand Down