wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-12 07:10:52 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Merge branch 'comfyanonymous:master' into master

Browse Source
This commit is contained in:
patientx 2025-10-11 01:18:58 +03:00 committed by GitHub
commit b7ebdcddcd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
comfy_extras/nodes_audio.py
View File

@ -142,9 +142,10 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
for key, value in metadata.items():
output_container.metadata[key] = value
layout = 'mono' if waveform.shape[0] == 1 else 'stereo'
# Set up the output stream with appropriate properties
if format == "opus":
out_stream = output_container.add_stream("libopus", rate=sample_rate)
out_stream = output_container.add_stream("libopus", rate=sample_rate, layout=layout)
if quality == "64k":
out_stream.bit_rate = 64000
elif quality == "96k":
@ -156,7 +157,7 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
elif quality == "320k":
out_stream.bit_rate = 320000
elif format == "mp3":
out_stream = output_container.add_stream("libmp3lame", rate=sample_rate)
out_stream = output_container.add_stream("libmp3lame", rate=sample_rate, layout=layout)
if quality == "V0":
#TODO i would really love to support V3 and V5 but there doesn't seem to be a way to set the qscale level, the property below is a bool
out_stream.codec_context.qscale = 1
@ -165,9 +166,9 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
elif quality == "320k":
out_stream.bit_rate = 320000
else: #format == "flac":
out_stream = output_container.add_stream("flac", rate=sample_rate)
out_stream = output_container.add_stream("flac", rate=sample_rate, layout=layout)
frame = av.AudioFrame.from_ndarray(waveform.movedim(0, 1).reshape(1, -1).float().numpy(), format='flt', layout='mono' if waveform.shape[0] == 1 else 'stereo')
frame = av.AudioFrame.from_ndarray(waveform.movedim(0, 1).reshape(1, -1).float().numpy(), format='flt', layout=layout)
frame.sample_rate = sample_rate
frame.pts = 0
output_container.mux(out_stream.encode(frame))