Merge branch 'master' into add-cla-workflow

Updated CLA workflow to modify permissions and action version.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

comfy_api/latest/_input_impl/video_types.py

@@ -1,6 +1,5 @@
 from av.container import InputContainer
 from av.subtitles.stream import SubtitleStream
-from av.video.reformatter import ColorRange
 from fractions import Fraction
 from typing import Optional
 from .._input import AudioInput, VideoInput
@@ -10,7 +9,6 @@ import itertools
 import json
 import numpy as np
 import math
-import os
 import torch
 from .._util import VideoContainer, VideoCodec, VideoComponents
 import logging
@@ -60,57 +58,6 @@ def video_stream_bit_depth(stream) -> int:
     return max(component.bits for component in stream.format.components)
 
 
-def last_decodable_audio_stream(container: InputContainer):
-    """Streams FFmpeg has no decoder for have no codec context, and decoding their
-    packets crashes the process (e.g. APAC spatial-audio track in iPhone)."""
-    stream = next(
-        (s for s in reversed(container.streams.audio) if s.codec_context is not None),
-        None,
-    )
-    if stream is None and len(container.streams.audio):
-        logging.warning("No decodable audio stream found in video; ignoring audio.")
-    return stream
-
-
-def probe_audio_params(container: InputContainer, audio_stream, max_packets: int = 200):
-    """Containers probed only up to a window (mpegts) leave audio codec parameters unset when
-    audio starts beyond it; learn them by decoding ahead. The caller must seek back afterwards.
-    Returns (sample_rate, channels), zeros when the stream never yields a decodable frame."""
-    for i, packet in enumerate(container.demux(audio_stream)):
-        try:
-            frames = packet.decode()
-        except av.error.FFmpegError:
-            return 0, 0
-        if frames:
-            return frames[0].sample_rate, frames[0].layout.nb_channels
-        if i >= max_packets:
-            break
-    return 0, 0
-
-
-def write_output_metadata(container: InputContainer, output, metadata: Optional[dict]):
-    """Copy the source container's metadata, then overlay the caller's tags."""
-    for key, value in container.metadata.items():
-        if metadata is None or key not in metadata:
-            output.metadata[key] = value
-    if metadata is not None:
-        for key, value in metadata.items():
-            output.metadata[key] = value if isinstance(value, str) else json.dumps(value)
-
-
-def mp4_output_open_kwargs(path: str | io.BytesIO, format: VideoContainer, codec: VideoCodec) -> dict:
-    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")
-    open_kwargs = {"mode": "w", "options": {"movflags": "use_metadata_tags"}}
-    if isinstance(format, VideoContainer) and format != VideoContainer.AUTO:
-        open_kwargs["format"] = format.value
-    elif isinstance(path, io.BytesIO):
-        open_kwargs["format"] = "mp4"  # no file extension to infer the format from
-    return open_kwargs
-
-
 class VideoFromFile(VideoInput):
     """
     Class representing video input from a file.
@@ -245,10 +192,13 @@ class VideoFromFile(VideoInput):
                     return estimated_frames
 
             # 3. Last resort: decode frames and count them (streaming)
-            start_time, duration = self.get_active_trim_window()
+            if self.__start_time < 0:
+                start_time = max(self._get_raw_duration() + self.__start_time, 0)
+            else:
+                start_time = self.__start_time
             frame_count = 1
             start_pts = int(start_time / video_stream.time_base)
-            end_pts = int((start_time + duration) / video_stream.time_base)
+            end_pts = int((start_time + self.__duration) / video_stream.time_base)
             container.seek(start_pts, stream=video_stream)
             frame_iterator = (
                 container.decode(video_stream)
@@ -303,14 +253,17 @@ class VideoFromFile(VideoInput):
 
     def get_components_internal(self, container: InputContainer) -> VideoComponents:
         video_stream = self._get_first_video_stream(container)
-        start_time, duration = self.get_active_trim_window()
+        if self.__start_time < 0:
+            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 + duration) / video_stream.time_base)
+        end_pts = int((start_time + self.__duration) / video_stream.time_base)
 
         if start_pts != 0:
             container.seek(start_pts, stream=video_stream)
@@ -328,8 +281,8 @@ class VideoFromFile(VideoInput):
         video_done = False
         audio_done = True
 
-        audio_stream = last_decodable_audio_stream(container)
-        if audio_stream is not None:
+        if len(container.streams.audio):
+            audio_stream = container.streams.audio[-1]
             streams += [audio_stream]
             resampler = av.audio.resampler.AudioResampler(format='fltp')
             audio_done = False
@@ -345,7 +298,7 @@ class VideoFromFile(VideoInput):
                     for frame in packet.decode():
                         if frame.pts < start_pts:
                             continue
-                        if duration and frame.pts >= end_pts:
+                        if self.__duration and frame.pts >= end_pts:
                             video_done = True
                             break
 
@@ -412,7 +365,7 @@ class VideoFromFile(VideoInput):
                     map(resampler.resample, packet.decode())
                 )
                 for frame in aframes:
-                    if duration and frame.time > start_time + duration:
+                    if self.__duration and frame.time > start_time + self.__duration:
                         audio_done = True
                         break
 
@@ -434,8 +387,8 @@ class VideoFromFile(VideoInput):
 
         if len(audio_frames) > 0:
             audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
-            if duration:
-                audio_data = audio_data[..., :int(duration * audio_stream.sample_rate)]
+            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({
@@ -481,22 +434,33 @@ class VideoFromFile(VideoInput):
             if not reuse_streams:
                 if bit_depth is None:
                     bit_depth = source_bit_depth
-                return self._save_transcoded(container, path, format=format, codec=codec, metadata=metadata, bit_depth=bit_depth)
+                components = self.get_components_internal(container)
+                video = VideoFromComponents(components)
+                return video.save_to(
+                    path, format=format, codec=codec, metadata=metadata, bit_depth=bit_depth,
+                )
 
             streams = container.streams
 
             open_kwargs = get_open_write_kwargs(path, container_format, format)
             with av.open(path, **open_kwargs) as output_container:
-                # Add metadata before writing any streams
-                write_output_metadata(container, output_container, metadata)
+                # 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 streams to the new container. Streams with no codec context cannot be used as an output template.
+                # 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)):
-                        if stream.codec_context is None:
-                            logging.warning("Skipping %s stream %d with unsupported codec", stream.type, stream.index)
-                            continue
                         out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
                         stream_map[stream] = out_stream
 
@@ -506,231 +470,6 @@ class VideoFromFile(VideoInput):
                         packet.stream = stream_map[packet.stream]
                         output_container.mux(packet)
 
-    def _save_transcoded(
-        self,
-        container: InputContainer,
-        path: str | io.BytesIO,
-        format: VideoContainer,
-        codec: VideoCodec,
-        metadata: Optional[dict],
-        bit_depth: int,
-    ):
-        """Re-encode to H.264/AAC one frame at a time; peak memory does not scale with video length."""
-        open_kwargs = mp4_output_open_kwargs(path, format, codec)
-        video_stream = self._get_first_video_stream(container)
-        start_time, duration = self.get_active_trim_window()
-        start_pts = int(start_time / video_stream.time_base)
-        end_pts = int((start_time + duration) / video_stream.time_base) if duration else None
-        if start_pts != 0:
-            container.seek(start_pts, stream=video_stream)
-
-        audio_stream = last_decodable_audio_stream(container)
-        pix_fmt = "yuv420p10le" if bit_depth >= 10 else "yuv420p"
-        rate = Fraction(video_stream.average_rate) if video_stream.average_rate else Fraction(1)
-
-        resampler = None
-        sample_rate = 0
-        audio_time_base = None
-        duration_cap = None
-        if audio_stream is not None:
-            sample_rate = audio_stream.codec_context.sample_rate
-            channels = audio_stream.codec_context.channels
-            if not sample_rate:
-                sample_rate, channels = probe_audio_params(container, audio_stream)
-                container.seek(start_pts, stream=video_stream)
-                if sample_rate:
-                    audio_stream.codec_context.flush_buffers()
-                else:
-                    logging.warning("Audio stream parameters could not be determined; ignoring audio.")
-                    audio_stream = None
-        if audio_stream is not None:
-            audio_time_base = Fraction(1, sample_rate)
-            layout = {1: "mono", 2: "stereo", 6: "5.1"}.get(channels, "stereo")
-            resampler = av.audio.resampler.AudioResampler(format="fltp", layout=layout, rate=sample_rate)
-            if duration:
-                duration_cap = math.ceil(duration * sample_rate)
-
-        streams = [video_stream] if audio_stream is None else [video_stream, audio_stream]
-        pts_step = max(1, int(round((1 / rate) / video_stream.time_base)))
-        video_done = False
-        audio_done = audio_stream is None
-        video_pts_offset = None
-        last_video_pts = None
-        source_size = None
-        rotation_k = 0
-        rotation_filter = None
-        audio_started = False
-        samples_written = 0
-        pending_audio = []
-        # The output opens lazily on the first kept frame: it decides the geometry (90/270 rotation swaps dims),
-        # and never seeking back keeps webm/mkv leading audio intact.
-        output = None
-        out_video = None
-        out_audio = None
-
-        def audio_frame_from_ndarray(nd_planar):
-            frame = av.AudioFrame.from_ndarray(np.ascontiguousarray(nd_planar), format="fltp", layout=layout)
-            frame.sample_rate = sample_rate
-            return frame
-
-        def drain_audio(final=False):
-            # Audio may cover the pts span of the video written so far, capped by the requested duration;
-            # frames/average_rate would misjudge VFR spans.
-            nonlocal samples_written, audio_done
-            if last_video_pts is None:
-                cap = 0
-            else:
-                cap = math.ceil((last_video_pts + pts_step) * video_stream.time_base * sample_rate)
-            if duration_cap is not None:
-                cap = min(cap, duration_cap)
-            while pending_audio and not audio_done:
-                frame = pending_audio[0]
-                if samples_written + frame.samples <= cap:
-                    frame.pts = samples_written
-                    frame.time_base = audio_time_base
-                    output.mux(out_audio.encode(frame))
-                    samples_written += frame.samples
-                    pending_audio.pop(0)
-                    continue
-                if final:
-                    keep = frame.to_ndarray()[..., :cap - samples_written]
-                    if keep.shape[-1] > 0:
-                        tail = audio_frame_from_ndarray(keep)
-                        tail.pts = samples_written
-                        tail.time_base = audio_time_base
-                        output.mux(out_audio.encode(tail))
-                        samples_written += keep.shape[-1]
-                    pending_audio.clear()
-                break
-            if duration_cap is not None and samples_written >= duration_cap:
-                audio_done = True
-            return cap
-
-        try:
-            for packet in container.demux(*streams):
-                if video_done and audio_done:
-                    break
-
-                if packet.stream == video_stream and not video_done:
-                    try:
-                        frames = packet.decode()
-                    except av.error.InvalidDataError:
-                        logging.info("pyav decode error")
-                        continue
-                    for frame in frames:
-                        if frame.pts is not None and frame.pts < start_pts:
-                            continue
-                        if end_pts is not None and frame.pts is not None and frame.pts >= end_pts:
-                            video_done = True
-                            break
-                        if output is None:
-                            rotation_k = int(round(frame.rotation // 90)) % 4 if frame.rotation else 0
-                            if rotation_k % 2:
-                                out_width, out_height = frame.height, frame.width
-                            else:
-                                out_width, out_height = frame.width, frame.height
-                            if out_width % 2 or out_height % 2:
-                                raise ValueError(f"H.264 output requires even dimensions, got {out_width}x{out_height}")
-                            source_size = (frame.width, frame.height)
-                            output = av.open(path, **open_kwargs)
-                            # Add metadata before writing any streams
-                            write_output_metadata(container, output, metadata)
-                            out_video = output.add_stream("h264", rate=rate)
-                            out_video.width = out_width
-                            out_video.height = out_height
-                            out_video.pix_fmt = pix_fmt
-                            # source pts pass through (rebased to 0), so variable frame rate survives
-                            out_video.codec_context.time_base = video_stream.time_base
-                            if audio_stream is not None:
-                                out_audio = output.add_stream("aac", rate=sample_rate, layout=layout)
-                        if (frame.width, frame.height) != source_size:
-                            # encoding would silently rescale the new geometry into the old one
-                            raise ValueError(
-                                f"Video resolution changes mid-stream "
-                                f"({source_size[0]}x{source_size[1]} -> {frame.width}x{frame.height}); cannot transcode"
-                            )
-                        if rotation_k:
-                            if rotation_filter is None:
-                                g = av.filter.Graph()
-                                g_src = g.add_buffer(width=frame.width, height=frame.height,
-                                                     format=frame.format.name, time_base=video_stream.time_base)
-                                tail = g_src
-                                for filter_name, filter_args in {1: [("transpose", "cclock")],
-                                                                 2: [("hflip", None), ("vflip", None)],
-                                                                 3: [("transpose", "clock")]}[rotation_k]:
-                                    step = g.add(filter_name, filter_args)
-                                    tail.link_to(step)
-                                    tail = step
-                                g_sink = g.add("buffersink")
-                                tail.link_to(g_sink)
-                                g.configure()
-                                rotation_filter = (g_src, g_sink)
-                            rotation_filter[0].push(frame)
-                            frame = rotation_filter[1].pull()
-                        if frame.color_range == ColorRange.JPEG:
-                            # compress full-range sources (yuvj/MJPEG) to limited range
-                            frame = frame.reformat(format=pix_fmt, src_color_range="JPEG", dst_color_range="MPEG")
-                        else:
-                            frame = frame.reformat(format=pix_fmt)
-                        if frame.pts is not None:
-                            if video_pts_offset is None:
-                                video_pts_offset = frame.pts
-                            frame.pts -= video_pts_offset
-                        if frame.pts is None or (last_video_pts is not None and frame.pts <= last_video_pts):
-                            # broken sources emit missing/backward timestamps mid-stream, which the
-                            # muxer rejects; nudge them forward by one nominal frame interval
-                            frame.pts = 0 if last_video_pts is None else last_video_pts + pts_step
-                        last_video_pts = frame.pts
-                        # the decoded pict_type would force x264's frame types (intra-only
-                        # sources like MJPEG/ProRes would come out all-keyframe)
-                        frame.pict_type = 0
-                        output.mux(out_video.encode(frame))
-                        drain_audio()
-
-                elif packet.stream == audio_stream and not audio_done:
-                    for resampled in itertools.chain.from_iterable(map(resampler.resample, packet.decode())):
-                        if not audio_started:
-                            if resampled.pts is None:
-                                frame_start = 0.0
-                            else:
-                                # passthrough frames keep the source stream's time base
-                                tb = resampled.time_base if resampled.time_base else audio_time_base
-                                frame_start = float(resampled.pts * tb)
-                            to_skip = max(0, int((start_time - frame_start) * sample_rate))
-                            if to_skip >= resampled.samples:
-                                continue
-                            audio_started = True
-                            if to_skip:
-                                pending_audio.append(audio_frame_from_ndarray(resampled.to_ndarray()[..., to_skip:]))
-                                continue
-                        pending_audio.append(resampled)
-                        if video_done:
-                            # the video window is complete so the cap is final, but containers
-                            # that interleave audio behind video (fragmented mp4) still owe most
-                            # of it: stop only once the demuxed audio covers the cap
-                            cap = drain_audio()
-                            if pending_audio or samples_written >= cap:
-                                drain_audio(final=True)
-                                audio_done = True
-                                break
-
-            if output is None:
-                raise ValueError(f"No decodable video frames found in file '{self.__file}'")
-            if out_audio is not None and not audio_done:
-                drain_audio(final=True)
-            output.mux(out_video.encode(None))
-            if out_audio is not None:
-                output.mux(out_audio.encode(None))
-        except BaseException:
-            if output is not None:
-                output.close()
-                if isinstance(path, (str, os.PathLike)) and os.path.exists(path):
-                    os.remove(path)
-            raise
-        else:
-            if output is not None:
-                output.close()
-
     def _get_first_video_stream(self, container: InputContainer):
         if len(container.streams.video):
             return container.streams.video[0]
@@ -778,12 +517,22 @@ class VideoFromComponents(VideoInput):
         bit_depth: int | None = None,
     ):
         """Save the video to a file path or BytesIO buffer."""
-        open_kwargs = mp4_output_open_kwargs(path, format, codec)
+        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")
         # None means "use the depth this video was created with" (CreateVideo's choice).
         if bit_depth is None:
             bit_depth = self.__bit_depth
         is_10bit = bit_depth >= 10
-        with av.open(path, **open_kwargs) as output:
+        extra_kwargs = {}
+        if isinstance(format, VideoContainer) and format != VideoContainer.AUTO:
+            extra_kwargs["format"] = format.value
+        elif isinstance(path, io.BytesIO):
+            # BytesIO has no file extension, so av.open can't infer the format.
+            # Default to mp4 since that's the only supported format anyway.
+            extra_kwargs["format"] = "mp4"
+        with av.open(path, mode='w', options={'movflags': 'use_metadata_tags'}, **extra_kwargs) as output:
             # Add metadata before writing any streams
             if metadata is not None:
                 for key, value in metadata.items():

comfy_api_nodes/util/upload_helpers.py

@@ -158,14 +158,7 @@ async def upload_video_to_comfyapi(
 
     # Convert VideoInput to BytesIO using specified container/codec
     video_bytes_io = BytesIO()
-    try:
-        video.save_to(video_bytes_io, format=container, codec=codec)
-    except Exception as e:
-        raise ValueError(
-            f"Could not convert the input video to {container.value.upper()} for upload; "
-            f"the file may be corrupted or use an unsupported codec. "
-            f"Try re-exporting it as MP4 (H.264). Original error: {e}"
-        ) from e
+    video.save_to(video_bytes_io, format=container, codec=codec)
     video_bytes_io.seek(0)
 
     return await upload_file_to_comfyapi(cls, video_bytes_io, filename, upload_mime_type, wait_label)

comfy_extras/nodes_text_overlay.py

@@ -1,150 +0,0 @@
-import numpy as np
-import torch
-from PIL import Image as PILImage, ImageColor, ImageDraw, ImageFont
-from typing_extensions import override
-
-from comfy_api.latest import ComfyExtension, IO
-
-
-class TextOverlay(IO.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return IO.Schema(
-            node_id="TextOverlay",
-            display_name="Draw Text Overlay",
-            category="text",
-            description="Draw text overlay on an image or batch of images.",
-            search_aliases=["text", "label", "caption", "subtitle", "watermark", "title", "addlabel", "overlay"],
-            inputs=[
-                IO.Image.Input("images"),
-                IO.String.Input("text", multiline=True, default=""),
-                IO.Float.Input("font_size", default=5.0, min=0.5, max=50.0, step=0.5, tooltip="Font size as a percentage of the image height."),
-                IO.Color.Input("color", default="#ffffff", tooltip="Color of the text."),
-                IO.Combo.Input("position", options=["top", "bottom"], default="top"),
-                IO.Combo.Input("align", options=["left", "center", "right"], default="left"),
-                IO.Boolean.Input("outline", default=True, tooltip="Draw a black outline around the text."),
-            ],
-            outputs=[IO.Image.Output(display_name="images")],
-        )
-
-    @classmethod
-    def execute(cls, images, text, font_size, color, position, align, outline) -> IO.NodeOutput:
-        if text.strip() == "":
-            return IO.NodeOutput(images)
-
-        text = text.replace("\\n", "\n").replace("\\t", "\t")
-
-        text_rgba = cls.parse_color_to_rgba(color)
-        outline_rgba = (0, 0, 0, 255) if outline else (0, 0, 0, 0)
-
-        # Render the overlay once and composite it across all frames in the batch
-        height = images.shape[1]
-        width = images.shape[2]
-        overlay_rgb, overlay_alpha = cls.render_overlay_text(width, height, text, position, align, font_size, text_rgba, outline_rgba)
-        overlay_rgb = overlay_rgb.to(device=images.device, dtype=images.dtype)
-        overlay_alpha = overlay_alpha.to(device=images.device, dtype=images.dtype)
-
-        result = images * (1.0 - overlay_alpha) + overlay_rgb * overlay_alpha
-        return IO.NodeOutput(result)
-
-    @staticmethod
-    def parse_color_to_rgba(color_string):
-        parsed = ImageColor.getrgb(color_string)
-
-        if len(parsed) == 3:
-            return (*parsed, 255)
-
-        return parsed
-
-    @classmethod
-    def render_overlay_text(cls, width, height, text, position, align, font_size, text_rgba, outline_rgba):
-        line_spacing = 1.2
-        margin_percent = 1.0
-        min_font_percent = 2.0
-        min_font_pixels = 10
-        outline_thickness_factor = 0.04
-
-        # Draw onto a transparent layer so the result can be alpha-composited over any frame.
-        layer = PILImage.new("RGBA", (width, height), (0, 0, 0, 0))
-        draw = ImageDraw.Draw(layer)
-
-        margin = int(round(margin_percent / 100.0 * min(width, height)))
-        max_width = max(1, width - 2 * margin)
-        max_height = max(1, height - 2 * margin)
-
-        # Font scales with resolution, then shrinks to fit the height.
-        size = max(1, int(round(font_size / 100.0 * height)))
-        floor = min(size, max(min_font_pixels, int(round(min_font_percent / 100.0 * height))))
-
-        while True:
-            font = ImageFont.load_default(size=size)
-            stroke = max(1, int(round(size * outline_thickness_factor))) if outline_rgba[3] > 0 else 0
-            block = "\n".join(cls.wrap_text(text, font, max_width))
-            # convert line spacing to pixel spacing
-            single = draw.textbbox((0, 0), "Ay", font=font, stroke_width=stroke)
-            double = draw.multiline_textbbox((0, 0), "Ay\nAy", font=font, spacing=0, stroke_width=stroke)
-            natural_advance = (double[3] - double[1]) - (single[3] - single[1])
-            pixel_spacing = int(round(size * line_spacing - natural_advance))
-            box = draw.multiline_textbbox((0, 0), block, font=font, spacing=pixel_spacing, stroke_width=stroke)
-            block_height = box[3] - box[1]
-
-            if block_height <= max_height or size <= floor:
-                break
-
-            size = max(floor, int(size * 0.9))
-
-        anchor_h, x = {"left": ("l", margin), "center": ("m", width / 2), "right": ("r", width - margin)}[align]
-
-        # Offset y so the rendered text sits flush against the margin
-        if position == "bottom":
-            y = height - margin - box[3]
-        else:
-            y = margin - box[1]
-
-        draw.multiline_text((x, y), block, font=font, fill=text_rgba, anchor=anchor_h + "a",
-                            align=align, spacing=pixel_spacing, stroke_width=stroke, stroke_fill=outline_rgba)
-
-        overlay = np.array(layer).astype(np.float32) / 255.0
-        overlay_rgb = torch.from_numpy(overlay[:, :, :3])
-        overlay_alpha = torch.from_numpy(overlay[:, :, 3:4])
-        return overlay_rgb, overlay_alpha
-
-    @staticmethod
-    def wrap_text(text, font, max_width):
-        lines = []
-        for raw_line in text.split("\n"):
-            words = raw_line.split()
-            if not words:
-                lines.append("")
-                continue
-            current = ""
-            # Break the line into words and split words that are too long
-            for word in words:
-                while font.getlength(word) > max_width and len(word) > 1:
-                    cut = 1
-                    while cut < len(word) and font.getlength(word[:cut + 1]) <= max_width:
-                        cut += 1
-                    if current:
-                        lines.append(current)
-                        current = ""
-                    lines.append(word[:cut])
-                    word = word[cut:]
-                candidate = word if not current else current + " " + word
-                if not current or font.getlength(candidate) <= max_width:
-                    current = candidate
-                else:
-                    lines.append(current)
-                    current = word
-            if current:
-                lines.append(current)
-        return lines
-
-
-class TextOverlayExtension(ComfyExtension):
-    @override
-    async def get_node_list(self) -> list[type[IO.ComfyNode]]:
-        return [TextOverlay]
-
-
-async def comfy_entrypoint() -> TextOverlayExtension:
-    return TextOverlayExtension()

nodes.py

@@ -2478,7 +2478,6 @@ async def init_builtin_extra_nodes():
         "nodes_glsl.py",
         "nodes_lora_debug.py",
         "nodes_textgen.py",
-        "nodes_text_overlay.py",
         "nodes_color.py",
         "nodes_toolkit.py",
         "nodes_replacements.py",

tests-unit/comfy_api_test/video_types_test.py

@@ -2,12 +2,11 @@ import pytest
 import torch
 import tempfile
 import os
-import sys
 import av
 import io
 from fractions import Fraction
 from comfy_api.input_impl.video_types import VideoFromFile, VideoFromComponents
-from comfy_api.util.video_types import VideoComponents, VideoContainer, VideoCodec
+from comfy_api.util.video_types import VideoComponents
 from comfy_api.input.basic_types import AudioInput
 from av.error import InvalidDataError
 
@@ -238,307 +237,3 @@ def test_duration_consistency(video_components):
     manual_duration = float(components.images.shape[0] / components.frame_rate)
 
     assert duration == pytest.approx(manual_duration)
-
-
-def create_transcode_source(
-    width=64, height=64, frames=30, fps=30, audio_streams=1, undecodable_audio=0, rotation=False,
-    container_format="mov", audio_codec="pcm_s16le",
-):
-    """Create a temp video that save_to must transcode (mpeg4 video, so codec != h264).
-
-    ``undecodable_audio`` trailing PCM streams get their fourcc corrupted so no decoder exists
-    (``codec_context is None``), like the APAC track in iPhone spatial-audio recordings.
-    ``rotation`` patches a 90-degree display matrix into the video track header.
-    """
-    buffer = io.BytesIO()
-    with av.open(buffer, mode="w", format=container_format) as container:
-        video_stream = container.add_stream("mpeg4", rate=fps)
-        video_stream.width = width
-        video_stream.height = height
-        video_stream.pix_fmt = "yuv420p"
-        audio = []
-        for _ in range(audio_streams + undecodable_audio):
-            stream = container.add_stream(audio_codec, rate=44100)
-            stream.sample_rate = 44100
-            audio.append(stream)
-
-        for i in range(frames):
-            frame = av.VideoFrame.from_ndarray(
-                torch.full((height, width, 3), (i * 7) % 256, dtype=torch.uint8).numpy(),
-                format="rgb24",
-            )
-            container.mux(video_stream.encode(frame.reformat(format="yuv420p")))
-        # write audio in 1024-sample frames, like real decoders produce, so the
-        # per-frame skip/cap logic in the transcode path actually runs
-        for stream in audio:
-            for offset in range(0, 44100 * frames // fps, 1024):
-                n = min(1024, 44100 * frames // fps - offset)
-                audio_frame = av.AudioFrame.from_ndarray(
-                    torch.zeros(1, n, dtype=torch.int16).numpy(), format="s16", layout="mono"
-                )
-                audio_frame.sample_rate = 44100
-                audio_frame.pts = offset
-                container.mux(stream.encode(audio_frame))
-        for stream in [video_stream, *audio]:
-            container.mux(stream.encode(None))
-
-    data = bytearray(buffer.getvalue())
-    end = len(data)
-    for _ in range(undecodable_audio):
-        end = data.rindex(b"sowt", 0, end)
-        data[end:end + 4] = b"Xpac"
-    if rotation:
-        # the 3x3 display matrix sits 40 bytes into the version-0 tkhd payload; first tkhd
-        # inside moov = video track (search from moov so mdat bytes can't false-match)
-        matrix_offset = data.index(b"tkhd", data.rindex(b"moov")) + 4 + 40
-        values = [0, 1 << 16, 0, -(1 << 16), 0, 0, 0, 0, 1 << 30]
-        data[matrix_offset:matrix_offset + 36] = b"".join(v.to_bytes(4, "big", signed=True) for v in values)
-
-    tmp = tempfile.NamedTemporaryFile(suffix=f".{container_format}", delete=False)
-    tmp.write(bytes(data))
-    tmp.close()
-    return tmp.name
-
-
-def transcode_and_probe(video):
-    buffer = io.BytesIO()
-    video.save_to(buffer, format=VideoContainer.MP4, codec=VideoCodec.H264)
-    buffer.seek(0)
-    with av.open(buffer) as container:
-        video_stream = container.streams.video[0]
-        audio_stream = container.streams.audio[0] if container.streams.audio else None
-        frames = 0
-        first_pts = None
-        for packet in container.demux(video_stream):
-            for frame in packet.decode():
-                if first_pts is None:
-                    first_pts = frame.pts
-                frames += 1
-        return {
-            "codec": video_stream.codec_context.name,
-            "width": video_stream.codec_context.width,
-            "height": video_stream.codec_context.height,
-            "frames": frames,
-            "first_pts": first_pts,
-            "video_seconds": float(video_stream.duration * video_stream.time_base) if video_stream.duration else None,
-            "audio_seconds": float(audio_stream.duration * audio_stream.time_base)
-            if audio_stream and audio_stream.duration else None,
-            "audio_codecs": [s.codec_context.name for s in container.streams.audio],
-        }
-
-
-def test_save_to_transcode_streams_without_buffering_frames():
-    """Transcoding must not decode the whole video into memory first (~2 GiB for this source)"""
-    resource = pytest.importorskip("resource")  # no getrusage on Windows
-    rss_scale = 1 if sys.platform == "darwin" else 1024  # ru_maxrss: bytes on macOS, KiB elsewhere
-    # ru_maxrss is a lifetime peak: a heavier test running earlier would shrink the measured
-    # delta and quietly defang this canary, so keep this source the biggest thing in the suite
-    file_path = create_transcode_source(width=640, height=480, frames=300)
-    try:
-        rss_before = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss * rss_scale
-        result = transcode_and_probe(VideoFromFile(file_path))
-        rss_delta = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss * rss_scale - rss_before
-
-        assert result["codec"] == "h264"
-        assert result["frames"] == 300
-        assert rss_delta < 500 * 2**20, f"transcode buffered frames in RAM (peak grew {rss_delta / 2**20:.0f} MiB)"
-    finally:
-        os.unlink(file_path)
-
-
-def test_save_to_transcode_honors_trim_window():
-    """start_time/duration trim applies to both video and audio on the streaming path"""
-    file_path = create_transcode_source(frames=90)  # 3s @ 30fps
-    try:
-        result = transcode_and_probe(VideoFromFile(file_path, start_time=1, duration=1))
-        assert result["frames"] == pytest.approx(30, abs=2)
-        assert result["first_pts"] == 0  # trimmed output is rebased to start at zero
-        assert result["video_seconds"] == pytest.approx(1.0, abs=0.1)
-        assert result["audio_seconds"] == pytest.approx(1.0, abs=0.1)
-    finally:
-        os.unlink(file_path)
-
-
-def test_save_to_transcode_keeps_audio_of_sparse_video():
-    """Audio that runs ahead of a sparse video track (slideshows, timelapses) must be
-    kept in full — it is only clamped to the video's end, never to the video cursor."""
-    buffer = io.BytesIO()
-    with av.open(buffer, mode="w", format="mp4") as container:
-        video_stream = container.add_stream("mpeg4", rate=30)
-        video_stream.width = video_stream.height = 64
-        video_stream.pix_fmt = "yuv420p"
-        audio_stream = container.add_stream("aac", rate=48000, layout="stereo")
-        for t in (0, 30, 60):  # 3 frames spread over 60 seconds
-            frame = av.VideoFrame.from_ndarray(
-                torch.full((64, 64, 3), t * 4, dtype=torch.uint8).numpy(), format="rgb24"
-            ).reformat(format="yuv420p")
-            frame.pts = t * 15360
-            frame.time_base = Fraction(1, 15360)
-            container.mux(video_stream.encode(frame))
-        container.mux(video_stream.encode(None))
-        for offset in range(0, 48000 * 60, 1024):
-            n = min(1024, 48000 * 60 - offset)
-            audio_frame = av.AudioFrame.from_ndarray(
-                torch.zeros(2, n, dtype=torch.float32).numpy(), format="fltp", layout="stereo"
-            )
-            audio_frame.sample_rate = 48000
-            audio_frame.pts = offset
-            audio_frame.time_base = Fraction(1, 48000)
-            container.mux(audio_stream.encode(audio_frame))
-        container.mux(audio_stream.encode(None))
-
-    buffer.seek(0)
-    result = transcode_and_probe(VideoFromFile(buffer))
-    assert result["audio_seconds"] == pytest.approx(60.0, abs=1.0)
-
-
-def test_save_to_transcode_vfr_audio_covers_video_span():
-    """A trim window in the sparse region of a VFR file keeps audio for the true pts span
-    of the kept frames. Deriving the span as frames/average_rate undercuts it badly: the
-    average is dominated by the dense region (and can be plain wrong on MediaRecorder files)."""
-    buffer = io.BytesIO()
-    with av.open(buffer, mode="w", format="mp4") as container:
-        video_stream = container.add_stream("mpeg4", rate=30)
-        video_stream.width = video_stream.height = 64
-        video_stream.pix_fmt = "yuv420p"
-        audio_stream = container.add_stream("aac", rate=48000, layout="stereo")
-        # 10 frames inside the first second, then one every 1.25 s
-        for i, t in enumerate([x / 10 for x in range(10)] + [1.0, 2.25, 3.5, 4.75]):
-            frame = av.VideoFrame.from_ndarray(
-                torch.full((64, 64, 3), (i * 16) % 256, dtype=torch.uint8).numpy(), format="rgb24"
-            ).reformat(format="yuv420p")
-            frame.pts = int(t * 15360)
-            frame.time_base = Fraction(1, 15360)
-            container.mux(video_stream.encode(frame))
-        container.mux(video_stream.encode(None))
-        for offset in range(0, 48000 * 6, 1024):
-            n = min(1024, 48000 * 6 - offset)
-            audio_frame = av.AudioFrame.from_ndarray(
-                torch.zeros(2, n, dtype=torch.float32).numpy(), format="fltp", layout="stereo"
-            )
-            audio_frame.sample_rate = 48000
-            audio_frame.pts = offset
-            audio_frame.time_base = Fraction(1, 48000)
-            container.mux(audio_stream.encode(audio_frame))
-        container.mux(audio_stream.encode(None))
-
-    buffer.seek(0)
-    result = transcode_and_probe(VideoFromFile(buffer, start_time=1, duration=5))
-    # kept frames: 1.0/2.25/3.5/4.75 s -> rebased span 3.75 s + one nominal interval
-    assert result["frames"] == 4
-    assert result["audio_seconds"] == pytest.approx(4.0, abs=0.45)
-
-
-def test_save_to_transcode_trims_audio_in_stream_time_base_units():
-    """Matroska audio timestamps tick in 1/1000, not 1/sample_rate; trim and audio timing
-    must convert through the frame's time base instead of assuming sample units. AAC audio,
-    because it decodes straight to the encoder's format and hits the resampler passthrough
-    that keeps the source time base on the frames."""
-    file_path = create_transcode_source(frames=90, container_format="matroska", audio_codec="aac")
-    try:
-        result = transcode_and_probe(VideoFromFile(file_path, start_time=1, duration=1))
-        assert result["audio_codecs"] == ["aac"]
-        assert result["video_seconds"] == pytest.approx(1.0, abs=0.1)
-        assert result["audio_seconds"] == pytest.approx(1.0, abs=0.1)
-    finally:
-        os.unlink(file_path)
-
-
-def test_save_to_transcode_learns_unprobed_audio_params():
-    """mpegts is only probed a few seconds deep at open, so an audio stream whose first
-    packet comes later (live captures where audio kicks in late) still has sample_rate 0
-    when the transcode starts; the parameters must be learned from the stream itself."""
-    sample_rate, fps, video_seconds, audio_start = 48000, 30, 13, 12
-    buffer = io.BytesIO()
-    with av.open(buffer, mode="w", format="mpegts") as container:
-        video_stream = container.add_stream("mpeg4", rate=fps)
-        video_stream.width = video_stream.height = 64
-        video_stream.pix_fmt = "yuv420p"
-        audio_stream = container.add_stream("aac", rate=sample_rate, layout="mono")
-        for i in range(video_seconds * fps):
-            frame = av.VideoFrame.from_ndarray(
-                torch.full((64, 64, 3), (i * 7) % 256, dtype=torch.uint8).numpy(), format="rgb24"
-            )
-            container.mux(video_stream.encode(frame.reformat(format="yuv420p")))
-        for offset in range(0, (video_seconds - audio_start) * sample_rate, 1024):
-            n = min(1024, (video_seconds - audio_start) * sample_rate - offset)
-            audio_frame = av.AudioFrame.from_ndarray(
-                torch.zeros(1, n, dtype=torch.float32).numpy(), format="fltp", layout="mono"
-            )
-            audio_frame.sample_rate = sample_rate
-            audio_frame.pts = audio_start * sample_rate + offset
-            container.mux(audio_stream.encode(audio_frame))
-        for stream in (video_stream, audio_stream):
-            container.mux(stream.encode(None))
-
-    buffer.seek(0)
-    with av.open(buffer) as container:
-        # the scenario requires unprobed parameters; if a future FFmpeg probes deeper,
-        # push audio_start/video_seconds further out to restore it
-        assert container.streams.audio[0].codec_context.sample_rate == 0
-    result = transcode_and_probe(VideoFromFile(buffer))
-    assert result["frames"] == video_seconds * fps
-    assert result["audio_codecs"] == ["aac"]
-    assert result["audio_seconds"] == pytest.approx(1.0, abs=0.1)
-
-
-def test_save_to_transcode_trimmed_fragmented_mp4_keeps_audio():
-    """Fragmented mp4 (MediaRecorder, DASH/HLS-derived files) delivers audio well behind
-    video, so when the trim window's last video frame arrives the audio demuxed so far
-    does not cover the window yet; the transcode must keep demuxing audio until it does
-    instead of finalizing on the first audio frame it sees afterwards."""
-    sample_rate, fps, seconds = 48000, 30, 6
-    buffer = io.BytesIO()
-    with av.open(buffer, mode="w", format="mp4", options={"movflags": "frag_keyframe+empty_moov"}) as container:
-        video_stream = container.add_stream("h264", rate=fps)
-        video_stream.width = video_stream.height = 64
-        video_stream.pix_fmt = "yuv420p"
-        audio_stream = container.add_stream("aac", rate=sample_rate, layout="mono")
-        next_audio_pts = 0
-        for i in range(seconds * fps):
-            frame = av.VideoFrame.from_ndarray(
-                torch.full((64, 64, 3), (i * 7) % 256, dtype=torch.uint8).numpy(), format="rgb24"
-            )
-            container.mux(video_stream.encode(frame.reformat(format="yuv420p")))
-            while next_audio_pts / sample_rate <= i / fps:  # feed audio alongside, like a live pipeline
-                audio_frame = av.AudioFrame.from_ndarray(
-                    torch.zeros(1, 1024, dtype=torch.float32).numpy(), format="fltp", layout="mono"
-                )
-                audio_frame.sample_rate = sample_rate
-                audio_frame.pts = next_audio_pts
-                container.mux(audio_stream.encode(audio_frame))
-                next_audio_pts += 1024
-        for stream in (video_stream, audio_stream):
-            container.mux(stream.encode(None))
-
-    result = transcode_and_probe(VideoFromFile(buffer, start_time=0.5, duration=1.0))
-    assert result["video_seconds"] == pytest.approx(1.0, abs=0.05)
-    assert result["audio_seconds"] == pytest.approx(1.0, abs=0.05)
-
-
-def test_save_to_transcode_bakes_rotation():
-    """A 90-degree display-matrix rotation swaps the output dimensions (portrait video)"""
-    file_path = create_transcode_source(width=64, height=32, rotation=True)
-    try:
-        result = transcode_and_probe(VideoFromFile(file_path))
-        assert (result["width"], result["height"]) == (32, 64)
-        assert result["frames"] == 30
-    finally:
-        os.unlink(file_path)
-
-
-def test_save_to_transcode_skips_undecodable_audio():
-    """Streaming transcode keeps the decodable audio track and drops undecodable ones;
-    with no decodable audio at all the output is video-only instead of crashing."""
-    mixed = all_bad = None
-    try:
-        mixed = create_transcode_source(audio_streams=1, undecodable_audio=1)
-        all_bad = create_transcode_source(audio_streams=0, undecodable_audio=2)
-        result = transcode_and_probe(VideoFromFile(mixed))
-        assert result["audio_codecs"] == ["aac"]
-        assert result["audio_seconds"] == pytest.approx(1.0, abs=0.1)
-        assert transcode_and_probe(VideoFromFile(all_bad))["audio_codecs"] == []
-    finally:
-        for path in (mixed, all_bad):
-            if path:
-                os.unlink(path)