Merge branch 'master' into asset-management

comfy_api/latest/_input_impl/video_types.py

@@ -8,6 +8,7 @@ import av
 import io
 import json
 import numpy as np
+import math
 import torch
 from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents
 
@@ -282,8 +283,6 @@ class VideoFromComponents(VideoInput):
             if self.__components.audio:
                 audio_sample_rate = int(self.__components.audio['sample_rate'])
                 audio_stream = output.add_stream('aac', rate=audio_sample_rate)
-                audio_stream.sample_rate = audio_sample_rate
-                audio_stream.format = 'fltp'
 
             # Encode video
             for i, frame in enumerate(self.__components.images):
@@ -298,27 +297,12 @@ class VideoFromComponents(VideoInput):
             output.mux(packet)
 
             if audio_stream and self.__components.audio:
-                # Encode audio
-                samples_per_frame = int(audio_sample_rate / frame_rate)
-                num_frames = self.__components.audio['waveform'].shape[2] // samples_per_frame
-                for i in range(num_frames):
-                    start = i * samples_per_frame
-                    end = start + samples_per_frame
-                    # TODO(Feature) - Add support for stereo audio
-                    chunk = (
-                        self.__components.audio["waveform"][0, 0, start:end]
-                        .unsqueeze(0)
-                        .contiguous()
-                        .numpy()
-                    )
-                    audio_frame = av.AudioFrame.from_ndarray(chunk, format='fltp', layout='mono')
-                    audio_frame.sample_rate = audio_sample_rate
-                    audio_frame.pts = i * samples_per_frame
-                    for packet in audio_stream.encode(audio_frame):
-                        output.mux(packet)
-
-                # Flush audio
-                for packet in audio_stream.encode(None):
-                    output.mux(packet)
-
+                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.sample_rate = audio_sample_rate
+                frame.pts = 0
+                output.mux(audio_stream.encode(frame))
 
+                # Flush encoder
+                output.mux(audio_stream.encode(None))

comfy_api/latest/_io.py

@@ -331,7 +331,7 @@ class String(ComfyTypeIO):
             })
 
 @comfytype(io_type="COMBO")
-class Combo(ComfyTypeI):
+class Combo(ComfyTypeIO):
     Type = str
     class Input(WidgetInput):
         """Combo input (dropdown)."""
@@ -360,6 +360,14 @@ class Combo(ComfyTypeI):
                 "remote": self.remote.as_dict() if self.remote else None,
             })
 
+    class Output(Output):
+        def __init__(self, id: str=None, display_name: str=None, options: list[str]=None, tooltip: str=None, is_output_list=False):
+            super().__init__(id, display_name, tooltip, is_output_list)
+            self.options = options if options is not None else []
+
+        @property
+        def io_type(self):
+            return self.options
 
 @comfytype(io_type="COMBO")
 class MultiCombo(ComfyTypeI):
@@ -740,6 +748,18 @@ class SEGS(ComfyTypeIO):
 class AnyType(ComfyTypeIO):
     Type = Any
 
+@comfytype(io_type="MODEL_PATCH")
+class MODEL_PATCH(ComfyTypeIO):
+    Type = Any
+
+@comfytype(io_type="AUDIO_ENCODER")
+class AudioEncoder(ComfyTypeIO):
+    Type = Any
+
+@comfytype(io_type="AUDIO_ENCODER_OUTPUT")
+class AudioEncoderOutput(ComfyTypeIO):
+    Type = Any
+
 @comfytype(io_type="COMFY_MULTITYPED_V3")
 class MultiType:
     Type = Any
@@ -1192,13 +1212,18 @@ class _ComfyNodeBaseInternal(_ComfyNodeInternal):
         raise NotImplementedError
 
     @classmethod
-    def validate_inputs(cls, **kwargs) -> bool:
-        """Optionally, define this function to validate inputs; equivalent to V1's VALIDATE_INPUTS."""
+    def validate_inputs(cls, **kwargs) -> bool | str:
+        """Optionally, define this function to validate inputs; equivalent to V1's VALIDATE_INPUTS.
+
+        If the function returns a string, it will be used as the validation error message for the node.
+        """
         raise NotImplementedError
 
     @classmethod
     def fingerprint_inputs(cls, **kwargs) -> Any:
-        """Optionally, define this function to fingerprint inputs; equivalent to V1's IS_CHANGED."""
+        """Optionally, define this function to fingerprint inputs; equivalent to V1's IS_CHANGED.
+
+        If this function returns the same value as last run, the node will not be executed."""
         raise NotImplementedError
 
     @classmethod
@@ -1594,6 +1619,7 @@ class _IO:
     Model = Model
     ClipVision = ClipVision
     ClipVisionOutput = ClipVisionOutput
+    AudioEncoderOutput = AudioEncoderOutput
     StyleModel = StyleModel
     Gligen = Gligen
     UpscaleModel = UpscaleModel