ComfyAPI Core v0.0.2 (#8962)

* ComfyAPI Core v0.0.2

* Respond to PR feedback

* Fix Python 3.9 errors

* Fix missing backward compatibility proxy

* Reorganize types a bit

The input types, input impls, and utility types are now all available in
the versioned API. See the change in `comfy_extras/nodes_video.py` for
an example of their usage.

* Remove the need for `--generate-api-stubs`

* Fix generated stubs differing by Python version

* Fix ruff formatting issues
This commit is contained in:
guill
2025-07-29 19:17:22 -07:00
committed by GitHub
parent 2f74e17975
commit 0a3d062e06
36 changed files with 2128 additions and 518 deletions

View File

@@ -0,0 +1,106 @@
from __future__ import annotations
from typing import Type, TYPE_CHECKING
from comfy_api.internal import ComfyAPIBase
from comfy_api.internal.singleton import ProxiedSingleton
from comfy_api.internal.async_to_sync import create_sync_class
from comfy_api.latest._input import ImageInput, AudioInput, MaskInput, LatentInput, VideoInput
from comfy_api.latest._input_impl import VideoFromFile, VideoFromComponents
from comfy_api.latest._util import VideoCodec, VideoContainer, VideoComponents
from comfy_execution.utils import get_executing_context
from comfy_execution.progress import get_progress_state, PreviewImageTuple
from PIL import Image
from comfy.cli_args import args
import numpy as np
class ComfyAPI_latest(ComfyAPIBase):
VERSION = "latest"
STABLE = False
class Execution(ProxiedSingleton):
async def set_progress(
self,
value: float,
max_value: float,
node_id: str | None = None,
preview_image: Image.Image | ImageInput | None = None,
ignore_size_limit: bool = False,
) -> None:
"""
Update the progress bar displayed in the ComfyUI interface.
This function allows custom nodes and API calls to report their progress
back to the user interface, providing visual feedback during long operations.
Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
"""
executing_context = get_executing_context()
if node_id is None and executing_context is not None:
node_id = executing_context.node_id
if node_id is None:
raise ValueError("node_id must be provided if not in executing context")
# Convert preview_image to PreviewImageTuple if needed
to_display: PreviewImageTuple | Image.Image | ImageInput | None = preview_image
if to_display is not None:
# First convert to PIL Image if needed
if isinstance(to_display, ImageInput):
# Convert ImageInput (torch.Tensor) to PIL Image
# Handle tensor shape [B, H, W, C] -> get first image if batch
tensor = to_display
if len(tensor.shape) == 4:
tensor = tensor[0]
# Convert to numpy array and scale to 0-255
image_np = (tensor.cpu().numpy() * 255).astype(np.uint8)
to_display = Image.fromarray(image_np)
if isinstance(to_display, Image.Image):
# Detect image format from PIL Image
image_format = to_display.format if to_display.format else "JPEG"
# Use None for preview_size if ignore_size_limit is True
preview_size = None if ignore_size_limit else args.preview_size
to_display = (image_format, to_display, preview_size)
get_progress_state().update_progress(
node_id=node_id,
value=value,
max_value=max_value,
image=to_display,
)
execution: Execution
class Input:
Image = ImageInput
Audio = AudioInput
Mask = MaskInput
Latent = LatentInput
Video = VideoInput
class InputImpl:
VideoFromFile = VideoFromFile
VideoFromComponents = VideoFromComponents
class Types:
VideoCodec = VideoCodec
VideoContainer = VideoContainer
VideoComponents = VideoComponents
ComfyAPI = ComfyAPI_latest
# Create a synchronous version of the API
if TYPE_CHECKING:
import comfy_api.latest.generated.ComfyAPISyncStub # type: ignore
ComfyAPISync: Type[comfy_api.latest.generated.ComfyAPISyncStub.ComfyAPISyncStub]
ComfyAPISync = create_sync_class(ComfyAPI_latest)
__all__ = [
"ComfyAPI",
"ComfyAPISync",
"Input",
"InputImpl",
"Types",
]

View File

@@ -0,0 +1,10 @@
from .basic_types import ImageInput, AudioInput, MaskInput, LatentInput
from .video_types import VideoInput
__all__ = [
"ImageInput",
"AudioInput",
"VideoInput",
"MaskInput",
"LatentInput",
]

View File

@@ -0,0 +1,42 @@
import torch
from typing import TypedDict, List, Optional
ImageInput = torch.Tensor
"""
An image in format [B, H, W, C] where B is the batch size, C is the number of channels,
"""
MaskInput = torch.Tensor
"""
A mask in format [B, H, W] where B is the batch size
"""
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 LatentInput(TypedDict):
"""
TypedDict representing latent input.
"""
samples: torch.Tensor
"""
Tensor in the format [B, C, H, W] where B is the batch size, C is the number of channels,
H is the height, and W is the width.
"""
noise_mask: Optional[MaskInput]
"""
Optional noise mask tensor in the same format as samples.
"""
batch_index: Optional[List[int]]

View File

@@ -0,0 +1,85 @@
from __future__ import annotations
from abc import ABC, abstractmethod
from typing import Optional, Union
import io
import av
from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
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
def get_stream_source(self) -> Union[str, io.BytesIO]:
"""
Get a streamable source for the video. This allows processing without
loading the entire video into memory.
Returns:
Either a file path (str) or a BytesIO object that can be opened with av.
Default implementation creates a BytesIO buffer, but subclasses should
override this for better performance when possible.
"""
buffer = io.BytesIO()
self.save_to(buffer)
buffer.seek(0)
return buffer
# Provide a default implementation, but subclasses can provide optimized versions
# if possible.
def get_dimensions(self) -> tuple[int, int]:
"""
Returns the dimensions of the video input.
Returns:
Tuple of (width, height)
"""
components = self.get_components()
return components.images.shape[2], components.images.shape[1]
def get_duration(self) -> float:
"""
Returns the duration of the video in seconds.
Returns:
Duration in seconds
"""
components = self.get_components()
frame_count = components.images.shape[0]
return float(frame_count / components.frame_rate)
def get_container_format(self) -> str:
"""
Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
Returns:
Container format as string
"""
# Default implementation - subclasses should override for better performance
source = self.get_stream_source()
with av.open(source, mode="r") as container:
return container.format.name

View File

@@ -0,0 +1,7 @@
from .video_types import VideoFromFile, VideoFromComponents
__all__ = [
# Implementations
"VideoFromFile",
"VideoFromComponents",
]

View File

@@ -0,0 +1,324 @@
from __future__ import annotations
from av.container import InputContainer
from av.subtitles.stream import SubtitleStream
from fractions import Fraction
from typing import Optional
from comfy_api.latest._input import AudioInput, VideoInput
import av
import io
import json
import numpy as np
import torch
from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents
def container_to_output_format(container_format: str | None) -> str | None:
"""
A container's `format` may be a comma-separated list of formats.
E.g., iso container's `format` may be `mov,mp4,m4a,3gp,3g2,mj2`.
However, writing to a file/stream with `av.open` requires a single format,
or `None` to auto-detect.
"""
if not container_format:
return None # Auto-detect
if "," not in container_format:
return container_format
formats = container_format.split(",")
return formats[0]
def get_open_write_kwargs(
dest: str | io.BytesIO, container_format: str, to_format: str | None
) -> dict:
"""Get kwargs for writing a `VideoFromFile` to a file/stream with `av.open`"""
open_kwargs = {
"mode": "w",
# If isobmff, preserve custom metadata tags (workflow, prompt, extra_pnginfo)
"options": {"movflags": "use_metadata_tags"},
}
is_write_to_buffer = isinstance(dest, io.BytesIO)
if is_write_to_buffer:
# Set output format explicitly, since it cannot be inferred from file extension
if to_format == VideoContainer.AUTO:
to_format = container_format.lower()
elif isinstance(to_format, str):
to_format = to_format.lower()
open_kwargs["format"] = container_to_output_format(to_format)
return open_kwargs
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_stream_source(self) -> str | io.BytesIO:
"""
Return the underlying file source for efficient streaming.
This avoids unnecessary memory copies when the source is already a file path.
"""
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0)
return self.__file
def get_dimensions(self) -> tuple[int, int]:
"""
Returns the dimensions of the video input.
Returns:
Tuple of (width, height)
"""
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0) # Reset the BytesIO object to the beginning
with av.open(self.__file, mode='r') as container:
for stream in container.streams:
if stream.type == 'video':
assert isinstance(stream, av.VideoStream)
return stream.width, stream.height
raise ValueError(f"No video stream found in file '{self.__file}'")
def get_duration(self) -> float:
"""
Returns the duration of the video in seconds.
Returns:
Duration in seconds
"""
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0)
with av.open(self.__file, mode="r") as container:
if container.duration is not None:
return float(container.duration / av.time_base)
# Fallback: calculate from frame count and frame rate
video_stream = next(
(s for s in container.streams if s.type == "video"), None
)
if video_stream and video_stream.frames and video_stream.average_rate:
return float(video_stream.frames / video_stream.average_rate)
# Last resort: decode frames to count them
if video_stream and video_stream.average_rate:
frame_count = 0
container.seek(0)
for packet in container.demux(video_stream):
for _ in packet.decode():
frame_count += 1
if frame_count > 0:
return float(frame_count / video_stream.average_rate)
raise ValueError(f"Could not determine duration for file '{self.__file}'")
def get_container_format(self) -> str:
"""
Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
Returns:
Container format as string
"""
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0)
with av.open(self.__file, mode='r') as container:
return container.format.name
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:
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0) # Reset the BytesIO object to the beginning
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 | io.BytesIO,
format: VideoContainer = VideoContainer.AUTO,
codec: VideoCodec = VideoCodec.AUTO,
metadata: Optional[dict] = None
):
if isinstance(self.__file, io.BytesIO):
self.__file.seek(0) # Reset the BytesIO object to the beginning
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
open_kwargs = get_open_write_kwargs(path, container_format, format)
with av.open(path, **open_kwargs) 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)
frame_rate = Fraction(round(self.__components.frame_rate * 1000), 1000)
# Create a video stream
video_stream = output.add_stream('h264', rate=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 / 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)

View File

@@ -0,0 +1,8 @@
from .video_types import VideoContainer, VideoCodec, VideoComponents
__all__ = [
# Utility Types
"VideoContainer",
"VideoCodec",
"VideoComponents",
]

View File

@@ -0,0 +1,52 @@
from __future__ import annotations
from dataclasses import dataclass
from enum import Enum
from fractions import Fraction
from typing import Optional
from comfy_api.latest._input import ImageInput, AudioInput
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

View File

@@ -0,0 +1,20 @@
from typing import Any, Dict, List, Optional, Tuple, Union, Set, Sequence, cast, NamedTuple
from comfy_api.latest import ComfyAPI_latest
from PIL.Image import Image
from torch import Tensor
class ComfyAPISyncStub:
def __init__(self) -> None: ...
class ExecutionSync:
def __init__(self) -> None: ...
"""
Update the progress bar displayed in the ComfyUI interface.
This function allows custom nodes and API calls to report their progress
back to the user interface, providing visual feedback during long operations.
Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
"""
def set_progress(self, value: float, max_value: float, node_id: Union[str, None] = None, preview_image: Union[Image, Tensor, None] = None, ignore_size_limit: bool = False) -> None: ...
execution: ExecutionSync