Add basic support for videos as types

This PR adds support for VIDEO as first-class types. In order to avoid
unnecessary costs, VIDEO outputs must implement the `VideoInput` ABC,
but their implementation details can vary. Included are two
implementations of this type which can be returned by other nodes:

* `VideoFromFile` - Created with either a path on disk (as a string) or
  a `io.BytesIO` containing the contents of a file in a supported format
  (like .mp4). This implementation won't actually load the video unless
  necessary. It will also avoid re-encoding when saving if possible.
* `VideoFromComponents` - Created from an image tensor and an optional
  audio tensor.

Currently, only h264 encoded videos in .mp4 containers are supported for
saving, but the plan is to add additional encodings/containers in the
near future (particularly .webm).

comfy/comfy_types/__init__.py

@@ -1,6 +1,7 @@
 import torch
 from typing import Callable, Protocol, TypedDict, Optional, List
 from .node_typing import IO, InputTypeDict, ComfyNodeABC, CheckLazyMixin, FileLocator
+from .input_types import ImageInput, AudioInput, VideoInput, VideoFromFile, VideoFromComponents, VideoContainer, VideoCodec, VideoComponents
 
 
 class UnetApplyFunction(Protocol):
@@ -43,4 +44,12 @@ __all__ = [
     ComfyNodeABC.__name__,
     CheckLazyMixin.__name__,
     FileLocator.__name__,
+    ImageInput.__name__,
+    AudioInput.__name__,
+    VideoInput.__name__,
+    VideoFromFile.__name__,
+    VideoFromComponents.__name__,
+    VideoContainer.__name__,
+    VideoCodec.__name__,
+    VideoComponents.__name__,
 ]

comfy/comfy_types/input_types.py

@@ -0,0 +1,292 @@
+from __future__ import annotations
+from abc import ABC, abstractmethod
+from av.container import InputContainer
+from av.subtitles.stream import SubtitleStream
+from dataclasses import dataclass
+from enum import Enum
+from fractions import Fraction
+from typing import Optional, TypedDict
+import av
+import io
+import json
+import numpy as np
+import torch
+
+ImageInput = torch.Tensor
+"""
+An image in format [B, H, W, C] where B is the batch size, C is the number of channels,
+"""
+
+class AudioInput(TypedDict):
+    """
+    TypedDict representing audio input.
+    """
+
+    waveform: torch.Tensor
+    """
+    Tensor in the format [B, C, T] where B is the batch size, C is the number of channels,
+    """
+
+    sample_rate: int
+
+class VideoCodec(str, Enum):
+    AUTO = "auto"
+    H264 = "h264"
+
+    @classmethod
+    def as_input(cls) -> list[str]:
+        """
+        Returns a list of codec names that can be used as node input.
+        """
+        return [member.value for member in cls]
+
+class VideoContainer(str, Enum):
+    AUTO = "auto"
+    MP4 = "mp4"
+
+    @classmethod
+    def as_input(cls) -> list[str]:
+        """
+        Returns a list of container names that can be used as node input.
+        """
+        return [member.value for member in cls]
+
+    @classmethod
+    def get_extension(cls, value) -> str:
+        """
+        Returns the file extension for the container.
+        """
+        if isinstance(value, str):
+            value = cls(value)
+        if value == VideoContainer.MP4 or value == VideoContainer.AUTO:
+            return "mp4"
+        return ""
+
+@dataclass
+class VideoComponents:
+    """
+    Dataclass representing the components of a video.
+    """
+
+    images: ImageInput
+    frame_rate: Fraction
+    audio: Optional[AudioInput] = None
+    metadata: Optional[dict] = None
+
+class VideoInput(ABC):
+    """
+    Abstract base class for video input types.
+    """
+
+    @abstractmethod
+    def get_components(self) -> VideoComponents:
+        """
+        Abstract method to get the video components (images, audio, and frame rate).
+
+        Returns:
+            VideoComponents containing images, audio, and frame rate
+        """
+        pass
+
+    @abstractmethod
+    def save_to(
+        self,
+        path: str,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        """
+        Abstract method to save the video input to a file.
+        """
+        pass
+
+class VideoFromFile(VideoInput):
+    """
+    Class representing video input from a file.
+    """
+
+    def __init__(self, file: str | io.BytesIO):
+        """
+        Initialize the VideoFromFile object based off of either a path on disk or a BytesIO object
+        containing the file contents.
+        """
+        self.file = file
+
+    def get_components_internal(self, container: InputContainer) -> VideoComponents:
+        # Get video frames
+        frames = []
+        for frame in container.decode(video=0):
+            img = frame.to_ndarray(format='rgb24')  # shape: (H, W, 3)
+            img = torch.from_numpy(img) / 255.0  # shape: (H, W, 3)
+            frames.append(img)
+
+        images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 3, 0, 0)
+
+        # Get frame rate
+        video_stream = next(s for s in container.streams if s.type == 'video')
+        frame_rate = Fraction(video_stream.average_rate) if video_stream and video_stream.average_rate else Fraction(1)
+
+        # Get audio if available
+        audio = None
+        try:
+            container.seek(0)  # Reset the container to the beginning
+            for stream in container.streams:
+                if stream.type != 'audio':
+                    continue
+                assert isinstance(stream, av.AudioStream)
+                audio_frames = []
+                for packet in container.demux(stream):
+                    for frame in packet.decode():
+                        assert isinstance(frame, av.AudioFrame)
+                        audio_frames.append(frame.to_ndarray())  # shape: (channels, samples)
+                if len(audio_frames) > 0:
+                    audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
+                    audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
+                    audio = AudioInput({
+                        "waveform": audio_tensor,
+                        "sample_rate": int(stream.sample_rate) if stream.sample_rate else 1,
+                    })
+        except StopIteration:
+            pass  # No audio stream
+
+        metadata = container.metadata
+        return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata)
+
+    def get_components(self) -> VideoComponents:
+        with av.open(self.file, mode='r') as container:
+            return self.get_components_internal(container)
+        raise ValueError(f"No video stream found in file '{self.file}'")
+
+    def save_to(
+        self,
+        path: str,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        with av.open(self.file, mode='r') as container:
+            container_format = container.format.name
+            video_encoding = container.streams.video[0].codec.name if len(container.streams.video) > 0 else None
+            reuse_streams = True
+            if format != VideoContainer.AUTO and format not in container_format.split(","):
+                reuse_streams = False
+            if codec != VideoCodec.AUTO and codec != video_encoding and video_encoding is not None:
+                reuse_streams = False
+
+            if not reuse_streams:
+                components = self.get_components_internal(container)
+                video = VideoFromComponents(components)
+                return video.save_to(
+                    path,
+                    format=format,
+                    codec=codec,
+                    metadata=metadata
+                )
+
+            streams = container.streams
+            with av.open(path, mode='w', options={"movflags": "use_metadata_tags"}) as output_container:
+                # Copy over the original metadata
+                for key, value in container.metadata.items():
+                    if metadata is None or key not in metadata:
+                        output_container.metadata[key] = value
+
+                # Add our new metadata
+                if metadata is not None:
+                    for key, value in metadata.items():
+                        if isinstance(value, str):
+                            output_container.metadata[key] = value
+                        else:
+                            output_container.metadata[key] = json.dumps(value)
+
+                # Add streams to the new container
+                stream_map = {}
+                for stream in streams:
+                    if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
+                        out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
+                        stream_map[stream] = out_stream
+
+                # Write packets to the new container
+                for packet in container.demux():
+                    if packet.stream in stream_map and packet.dts is not None:
+                        packet.stream = stream_map[packet.stream]
+                        output_container.mux(packet)
+
+class VideoFromComponents(VideoInput):
+    """
+    Class representing video input from tensors.
+    """
+
+    def __init__(self, components: VideoComponents):
+        self.components = components
+
+    def get_components(self) -> VideoComponents:
+        return VideoComponents(
+            images=self.components.images,
+            audio=self.components.audio,
+            frame_rate=self.components.frame_rate
+        )
+
+    def save_to(
+        self,
+        path: str,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        if format != VideoContainer.AUTO and format != VideoContainer.MP4:
+            raise ValueError("Only MP4 format is supported for now")
+        if codec != VideoCodec.AUTO and codec != VideoCodec.H264:
+            raise ValueError("Only H264 codec is supported for now")
+        with av.open(path, mode='w', options={'movflags': 'use_metadata_tags'}) as output:
+            # Add metadata before writing any streams
+            if metadata is not None:
+                for key, value in metadata.items():
+                    output.metadata[key] = json.dumps(value)
+
+            # Create a video stream
+            video_stream = output.add_stream('h264', rate=self.components.frame_rate)
+            video_stream.width = self.components.images.shape[2]
+            video_stream.height = self.components.images.shape[1]
+            video_stream.pix_fmt = 'yuv420p'
+
+            # Create an audio stream
+            audio_sample_rate = 1
+            audio_stream: Optional[av.AudioStream] = None
+            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):
+                img = (frame * 255).clamp(0, 255).byte().cpu().numpy() # shape: (H, W, 3)
+                frame = av.VideoFrame.from_ndarray(img, format='rgb24')
+                frame = frame.reformat(format='yuv420p')  # Convert to YUV420P as required by h264
+                packet = video_stream.encode(frame)
+                output.mux(packet)
+
+            # Flush video
+            packet = video_stream.encode(None)
+            output.mux(packet)
+
+            if audio_stream and self.components.audio:
+                # Encode audio
+                samples_per_frame = int(audio_sample_rate / self.components.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).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)
+

comfy/comfy_types/node_typing.py

@@ -48,6 +48,7 @@ class IO(StrEnum):
     FACE_ANALYSIS = "FACE_ANALYSIS"
     BBOX = "BBOX"
     SEGS = "SEGS"
+    VIDEO = "VIDEO"
 
     ANY = "*"
     """Always matches any type, but at a price.
@@ -292,7 +293,7 @@ class ComfyNodeABC(ABC):
     Comfy Docs: https://docs.comfy.org/custom-nodes/backend/lists#list-processing
     """
 
-    RETURN_TYPES: tuple[IO]
+    RETURN_TYPES: tuple[IO] | tuple[()]
     """A tuple representing the outputs of this node.
 
     Usage::
@@ -301,12 +302,12 @@ class ComfyNodeABC(ABC):
 
     Comfy Docs: https://docs.comfy.org/custom-nodes/backend/server_overview#return-types
     """
-    RETURN_NAMES: tuple[str]
+    RETURN_NAMES: tuple[str] | tuple[()]
     """The output slot names for each item in `RETURN_TYPES`, e.g. ``RETURN_NAMES = ("count", "filter_string")``
 
     Comfy Docs: https://docs.comfy.org/custom-nodes/backend/server_overview#return-names
     """
-    OUTPUT_TOOLTIPS: tuple[str]
+    OUTPUT_TOOLTIPS: tuple[str] | tuple[()]
     """A tuple of strings to use as tooltips for node outputs, one for each item in `RETURN_TYPES`."""
     FUNCTION: str
     """The name of the function to execute as a literal string, e.g. `FUNCTION = "execute"`

comfy_extras/nodes_video.py

@@ -5,9 +5,10 @@ import av
 import torch
 import folder_paths
 import json
+from typing import Optional, Literal
 from fractions import Fraction
-from comfy.comfy_types import FileLocator
+from comfy.comfy_types import IO, FileLocator, ComfyNodeABC, VideoInput, AudioInput, ImageInput, VideoFromComponents, VideoContainer, VideoCodec, VideoComponents
-
+from comfy.cli_args import args
 
 class SaveWEBM:
     def __init__(self):
@@ -75,7 +76,130 @@ class SaveWEBM:
 
         return {"ui": {"images": results, "animated": (True,)}}  # TODO: frontend side
 
+class SaveVideo(ComfyNodeABC):
+    def __init__(self):
+        self.output_dir = folder_paths.get_output_directory()
+        self.type: Literal["output"] = "output"
+        self.prefix_append = ""
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "video": (IO.VIDEO, {"tooltip": "The video to save."}),
+                "filename_prefix": ("STRING", {"default": "video/ComfyUI", "tooltip": "The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."}),
+                "format": (VideoContainer.as_input(), {"default": "auto", "tooltip": "The format to save the video as."}),
+                "codec": (VideoCodec.as_input(), {"default": "auto", "tooltip": "The codec to use for the video."}),
+            },
+            "hidden": {
+                "prompt": "PROMPT",
+                "extra_pnginfo": "EXTRA_PNGINFO"
+            },
+        }
+
+    RETURN_TYPES = ()
+    FUNCTION = "save_video"
+
+    OUTPUT_NODE = True
+
+    CATEGORY = "image/video"
+    DESCRIPTION = "Saves the input images to your ComfyUI output directory."
+
+    def save_video(self, video: VideoInput, filename_prefix, format, codec, prompt=None, extra_pnginfo=None):
+        filename_prefix += self.prefix_append
+        components = video.get_components()
+        width = components.images.shape[2]
+        height = components.images.shape[1]
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
+            filename_prefix,
+            self.output_dir,
+            width,
+            height
+        )
+        results: list[FileLocator] = list()
+        saved_metadata = None
+        if not args.disable_metadata:
+            metadata = {}
+            if extra_pnginfo is not None:
+                metadata.update(extra_pnginfo)
+            if prompt is not None:
+                metadata["prompt"] = prompt
+            if len(metadata) > 0:
+                saved_metadata = metadata
+        file = f"{filename}_{counter:05}_.{VideoContainer.get_extension(format)}"
+        video.save_to(
+            os.path.join(full_output_folder, file),
+            format=format,
+            codec=codec,
+            metadata=saved_metadata
+        )
+
+        results.append({
+            "filename": file,
+            "subfolder": subfolder,
+            "type": self.type
+        })
+        counter += 1
+
+        return { "ui": { "images": results, "animated": (True,) } }
+
+class CreateVideo(ComfyNodeABC):
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "images": (IO.IMAGE, {"tooltip": "The images to create a video from."}),
+                "fps": ("FLOAT", {"default": 30.0, "min": 1.0, "max": 120.0, "step": 1.0}),
+            },
+            "optional": {
+                "audio": (IO.AUDIO, {"tooltip": "The audio to add to the video."}),
+            }
+        }
+
+    RETURN_TYPES = (IO.VIDEO,)
+    FUNCTION = "create_video"
+
+    CATEGORY = "image/video"
+    DESCRIPTION = "Create a video from images."
+
+    def create_video(self, images: ImageInput, fps: float, audio: Optional[AudioInput] = None):
+        return (VideoFromComponents(
+            VideoComponents(
+            images=images,
+            audio=audio,
+            frame_rate=Fraction(fps),
+            )
+        ),)
+
+class GetVideoComponents(ComfyNodeABC):
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "video": (IO.VIDEO, {"tooltip": "The video to extract components from."}),
+            }
+        }
+    RETURN_TYPES = (IO.IMAGE, IO.AUDIO, IO.FLOAT)
+    RETURN_NAMES = ("images", "audio", "fps")
+    FUNCTION = "get_components"
+
+    CATEGORY = "image/video"
+    DESCRIPTION = "Extracts all components from a video: frames, audio, and framerate."
+
+    def get_components(self, video: VideoInput):
+        components = video.get_components()
+
+        return (components.images, components.audio, float(components.frame_rate))
 
 NODE_CLASS_MAPPINGS = {
     "SaveWEBM": SaveWEBM,
+    "SaveVideo": SaveVideo,
+    "CreateVideo": CreateVideo,
+    "GetVideoComponents": GetVideoComponents,
+}
+
+NODE_DISPLAY_NAME_MAPPINGS = {
+    "SaveVideo": "Save Video",
+    "CreateVideo": "Create Video",
+    "GetVideoComponents": "Get Video Components",
 }