Merge remote-tracking branch 'origin/master' into feature/generic-feature-flag-cli

comfy_api/input/__init__.py

@@ -9,6 +9,7 @@ from comfy_api.latest._input import (
     CurveInput,
     MonotoneCubicCurve,
     LinearCurve,
+    RangeInput,
 )
 
 __all__ = [
@@ -21,4 +22,5 @@ __all__ = [
     "CurveInput",
     "MonotoneCubicCurve",
     "LinearCurve",
+    "RangeInput",
 ]

comfy_api/latest/_input/__init__.py

@@ -1,5 +1,6 @@
 from .basic_types import ImageInput, AudioInput, MaskInput, LatentInput
 from .curve_types import CurvePoint, CurveInput, MonotoneCubicCurve, LinearCurve
+from .range_types import RangeInput
 from .video_types import VideoInput
 
 __all__ = [
@@ -12,4 +13,5 @@ __all__ = [
     "CurveInput",
     "MonotoneCubicCurve",
     "LinearCurve",
+    "RangeInput",
 ]

comfy_api/latest/_input/range_types.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import logging
+import math
+import numpy as np
+
+logger = logging.getLogger(__name__)
+
+
+class RangeInput:
+    """Represents a levels/range adjustment: input range [min, max] with
+    optional midpoint (gamma control).
+
+    Generates a 1D LUT identical to GIMP's levels mapping:
+        1. Normalize input to [0, 1] using [min, max]
+        2. Apply gamma correction: pow(value, 1/gamma)
+        3. Clamp to [0, 1]
+
+    The midpoint field is a position in [0, 1] representing where the
+    midtone falls within [min, max]. It maps to gamma via:
+        gamma = -log2(midpoint)
+    So midpoint=0.5 → gamma=1.0 (linear).
+    """
+
+    def __init__(self, min_val: float, max_val: float, midpoint: float | None = None):
+        self.min_val = min_val
+        self.max_val = max_val
+        self.midpoint = midpoint
+
+    @staticmethod
+    def from_raw(data) -> RangeInput:
+        if isinstance(data, RangeInput):
+            return data
+        if isinstance(data, dict):
+            return RangeInput(
+                min_val=float(data.get("min", 0.0)),
+                max_val=float(data.get("max", 1.0)),
+                midpoint=float(data["midpoint"]) if data.get("midpoint") is not None else None,
+            )
+        raise TypeError(f"Cannot convert {type(data)} to RangeInput")
+
+    def to_lut(self, size: int = 256) -> np.ndarray:
+        """Generate a float64 lookup table mapping [0, 1] input through this
+        levels adjustment.
+
+        The LUT maps normalized input values (0..1) to output values (0..1),
+        matching the GIMP levels formula.
+        """
+        xs = np.linspace(0.0, 1.0, size, dtype=np.float64)
+
+        in_range = self.max_val - self.min_val
+        if abs(in_range) < 1e-10:
+            return np.where(xs >= self.min_val, 1.0, 0.0).astype(np.float64)
+
+        # Normalize: map [min, max] → [0, 1]
+        result = (xs - self.min_val) / in_range
+        result = np.clip(result, 0.0, 1.0)
+
+        # Gamma correction from midpoint
+        if self.midpoint is not None and self.midpoint > 0 and self.midpoint != 0.5:
+            gamma = max(-math.log2(self.midpoint), 0.001)
+            inv_gamma = 1.0 / gamma
+            mask = result > 0
+            result[mask] = np.power(result[mask], inv_gamma)
+
+        return result
+
+    def __repr__(self) -> str:
+        mid = f", midpoint={self.midpoint}" if self.midpoint is not None else ""
+        return f"RangeInput(min={self.min_val}, max={self.max_val}{mid})"

comfy_api/latest/_input_impl/video_types.py

@@ -12,6 +12,7 @@ import numpy as np
 import math
 import torch
 from .._util import VideoContainer, VideoCodec, VideoComponents
+import logging
 
 
 def container_to_output_format(container_format: str | None) -> str | None:
@@ -238,64 +239,125 @@ class VideoFromFile(VideoInput):
             start_time = max(self._get_raw_duration() + self.__start_time, 0)
         else:
             start_time = self.__start_time
+
         # Get video frames
         frames = []
+        audio_frames = []
+        alphas = None
         start_pts = int(start_time / video_stream.time_base)
         end_pts = int((start_time + self.__duration) / video_stream.time_base)
-        container.seek(start_pts, stream=video_stream)
-        for frame in container.decode(video_stream):
-            if frame.pts < start_pts:
-                continue
-            if self.__duration and frame.pts >= end_pts:
-                break
-            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)
+        if start_pts != 0:
+            container.seek(start_pts, stream=video_stream)
+
+        image_format = 'gbrpf32le'
+        process_image_format = lambda a: a
+        audio = None
+
+        streams = [video_stream]
+        has_first_audio_frame = False
+        checked_alpha = False
+
+        # Default to False so we decode until EOF if duration is 0
+        video_done = False
+        audio_done = True
+
+        if len(container.streams.audio):
+            audio_stream = container.streams.audio[-1]
+            streams += [audio_stream]
+            resampler = av.audio.resampler.AudioResampler(format='fltp')
+            audio_done = False
+
+        for packet in container.demux(*streams):
+            if video_done and audio_done:
+                break
+
+            if packet.stream.type == "video":
+                if video_done:
+                    continue
+                try:
+                    for frame in packet.decode():
+                        if frame.pts < start_pts:
+                            continue
+                        if self.__duration and frame.pts >= end_pts:
+                            video_done = True
+                            break
+
+                        if not checked_alpha:
+                            alpha_channel = False
+                            for comp in frame.format.components:
+                                if comp.is_alpha or frame.format.name == "pal8":
+                                    alphas = []
+                                    alpha_channel = True
+                                    break
+                            if frame.format.name in ("yuvj420p", "yuvj422p", "yuvj444p", "rgb24", "rgba", "pal8"):
+                                process_image_format = lambda a: a.float() / 255.0
+                                if alpha_channel:
+                                    image_format = 'rgba'
+                                else:
+                                    image_format = 'rgb24'
+                            else:
+                                process_image_format = lambda a: a
+                                if alpha_channel:
+                                    image_format = 'gbrapf32le'
+                                else:
+                                    image_format = 'gbrpf32le'
+
+                            checked_alpha = True
+
+                        img = frame.to_ndarray(format=image_format)  # shape: (H, W, 4)
+                        if frame.rotation != 0:
+                            k = int(round(frame.rotation // 90))
+                            img = np.rot90(img, k=k, axes=(0, 1)).copy()
+                        if alphas is None:
+                            frames.append(torch.from_numpy(img))
+                        else:
+                            frames.append(torch.from_numpy(img[..., :-1]))
+                            alphas.append(torch.from_numpy(img[..., -1:]))
+                except av.error.InvalidDataError:
+                    logging.info("pyav decode error")
+
+            elif packet.stream.type == "audio":
+                if audio_done:
+                    continue
+
+                aframes = itertools.chain.from_iterable(
+                    map(resampler.resample, packet.decode())
+                )
+                for frame in aframes:
+                    if self.__duration and frame.time > start_time + self.__duration:
+                        audio_done = True
+                        break
+
+                    if not has_first_audio_frame:
+                        offset_seconds = start_time - frame.pts * audio_stream.time_base
+                        to_skip = max(0, int(offset_seconds * audio_stream.sample_rate))
+                        if to_skip < frame.samples:
+                            has_first_audio_frame = True
+                            audio_frames.append(frame.to_ndarray()[..., to_skip:])
+                    else:
+                        audio_frames.append(frame.to_ndarray())
+
+        images = process_image_format(torch.stack(frames)) if len(frames) > 0 else torch.zeros(0, 0, 0, 3)
+        if alphas is not None:
+            alphas = process_image_format(torch.stack(alphas)) if len(alphas) > 0 else torch.zeros(0, 0, 0, 1)
 
         # Get frame rate
         frame_rate = Fraction(video_stream.average_rate) if video_stream.average_rate else Fraction(1)
 
-        # Get audio if available
-        audio = None
-        container.seek(start_pts, stream=video_stream)
-        # Use last stream for consistency
-        if len(container.streams.audio):
-            audio_stream = container.streams.audio[-1]
-            audio_frames = []
-            resample = av.audio.resampler.AudioResampler(format='fltp').resample
-            frames = itertools.chain.from_iterable(
-                map(resample, container.decode(audio_stream))
-            )
+        if len(audio_frames) > 0:
+            audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
+            if self.__duration:
+                audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)]
 
-            has_first_frame = False
-            for frame in frames:
-                offset_seconds = start_time - frame.pts * audio_stream.time_base
-                to_skip = max(0, int(offset_seconds * audio_stream.sample_rate))
-                if to_skip < frame.samples:
-                    has_first_frame = True
-                    break
-            if has_first_frame:
-                audio_frames.append(frame.to_ndarray()[..., to_skip:])
-
-            for frame in frames:
-                if self.__duration and frame.time > start_time + self.__duration:
-                    break
-                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)
-                if self.__duration:
-                    audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)]
-
-                audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
-                audio = AudioInput({
-                    "waveform": audio_tensor,
-                    "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1,
-                })
+            audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
+            audio = AudioInput({
+                "waveform": audio_tensor,
+                "sample_rate": int(audio_stream.sample_rate) if audio_stream.sample_rate else 1,
+            })
 
         metadata = container.metadata
-        return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata)
+        return VideoComponents(images=images, alpha=alphas, audio=audio, frame_rate=frame_rate, metadata=metadata)
 
     def get_components(self) -> VideoComponents:
         if isinstance(self.__file, io.BytesIO):

comfy_api/latest/_io.py

@@ -1266,6 +1266,43 @@ class Histogram(ComfyTypeIO):
     Type = list[int]
 
 
+@comfytype(io_type="RANGE")
+class Range(ComfyTypeIO):
+    from comfy_api.input import RangeInput
+    if TYPE_CHECKING:
+        Type = RangeInput
+
+    class Input(WidgetInput):
+        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
+                     socketless: bool=True, default: dict=None,
+                     display: str=None,
+                     gradient_stops: list=None,
+                     show_midpoint: bool=None,
+                     midpoint_scale: str=None,
+                     value_min: float=None,
+                     value_max: float=None,
+                     advanced: bool=None):
+            super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
+            if default is None:
+                self.default = {"min": 0.0, "max": 1.0}
+            self.display = display
+            self.gradient_stops = gradient_stops
+            self.show_midpoint = show_midpoint
+            self.midpoint_scale = midpoint_scale
+            self.value_min = value_min
+            self.value_max = value_max
+
+        def as_dict(self):
+            return super().as_dict() | prune_dict({
+                "display": self.display,
+                "gradient_stops": self.gradient_stops,
+                "show_midpoint": self.show_midpoint,
+                "midpoint_scale": self.midpoint_scale,
+                "value_min": self.value_min,
+                "value_max": self.value_max,
+            })
+
+
 DYNAMIC_INPUT_LOOKUP: dict[str, Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]] = {}
 def register_dynamic_input_func(io_type: str, func: Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]):
     DYNAMIC_INPUT_LOOKUP[io_type] = func
@@ -2276,5 +2313,6 @@ __all__ = [
     "BoundingBox",
     "Curve",
     "Histogram",
+    "Range",
     "NodeReplace",
 ]

comfy_api/latest/_util/video_types.py

@@ -3,7 +3,7 @@ from dataclasses import dataclass
 from enum import Enum
 from fractions import Fraction
 from typing import Optional
-from .._input import ImageInput, AudioInput
+from .._input import ImageInput, AudioInput, MaskInput
 
 class VideoCodec(str, Enum):
     AUTO = "auto"
@@ -48,5 +48,4 @@ class VideoComponents:
     frame_rate: Fraction
     audio: Optional[AudioInput] = None
     metadata: Optional[dict] = None
-
-
+    alpha: Optional[MaskInput] = None