Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

fix: use .cpu() for waveform conversion in AudioFrame creation (#11787)

Theephop0fd10ffa0958
diff --git a/comfy_api/latest/_input_impl/video_types.py b/comfy_api/latest/_input_impl/video_types.py
index ea35c6062..1405d0b81 100644
--- a/comfy_api/latest/_input_impl/video_types.py
+++ b/comfy_api/latest/_input_impl/video_types.py
@@ -374,7 +374,7 @@ class VideoFromComponents(VideoInput):
if audio_stream and self.__components.audio:
waveform = self.__components.audio['waveform']
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().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
+ 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.pts = 0
output.mux(audio_stream.encode(frame))