wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-09 04:52:32 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Support 5.1 audio layout on save
Some checks failed
Python Linting / Run Ruff (push) Has been cancelled
Details
Python Linting / Run Pylint (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Austin Mroz 2026-02-06 19:19:31 -08:00
parent 8de2aecb03
commit c202105939
No known key found for this signature in database
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_api/latest/_input_impl/video_types.py
View File

@ -426,7 +426,10 @@ class VideoFromComponents(VideoInput):
audio_stream: Optional[av.AudioStream] = None audio_stream: Optional[av.AudioStream] = None
if self.__components.audio: if self.__components.audio:
audio_sample_rate = int(self.__components.audio['sample_rate']) audio_sample_rate = int(self.__components.audio['sample_rate'])
audio_stream = output.add_stream('aac', rate=audio_sample_rate) waveform = self.__components.audio['waveform']
waveform = waveform[0, :, :math.ceil((audio_sample_rate / frame_rate) * self.__components.images.shape[0])]
layout = {1: 'mono', 2: 'stereo', 6: '5.1'}.get(waveform.shape[0], 'stereo')
audio_stream = output.add_stream('aac', rate=audio_sample_rate, layout=layout)
# Encode video # Encode video
for i, frame in enumerate(self.__components.images): for i, frame in enumerate(self.__components.images):
@ -441,9 +444,7 @@ class VideoFromComponents(VideoInput):
output.mux(packet) output.mux(packet)
if audio_stream and self.__components.audio: if audio_stream and self.__components.audio:
waveform = self.__components.audio['waveform'] frame = av.AudioFrame.from_ndarray(waveform.float().cpu().numpy(), format='fltp', layout=layout)
waveform = waveform[:, :, :math.ceil((audio_sample_rate / frame_rate) * self.__components.images.shape[0])]
frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().cpu().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
frame.sample_rate = audio_sample_rate frame.sample_rate = audio_sample_rate
frame.pts = 0 frame.pts = 0
output.mux(audio_stream.encode(frame)) output.mux(audio_stream.encode(frame))