Merge branch 'master' into feat/torchao-int4

comfy/ldm/hidream_o1/attention.py

@@ -15,24 +15,24 @@ def make_two_pass_attention(ar_len: int, transformer_options=None):
     The AR pass goes through SDPA directand bypasses wrappers, it is only ~1% of T at typical edit sizes.
     """
 
-    def two_pass_attention(q, k, v, heads, **kwargs):
+    def two_pass_attention(q, k, v, heads, enable_gqa=False, **kwargs):
         B, H, T, D = q.shape
 
         if T < k.shape[2]: # KV-cache hot path: Q is shorter than K/V (cached AR prefix is in K/V only), all fresh Q positions are in the gen region, single full-attention call
-            out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
+            out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
         elif ar_len >= T:
-            out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True)
+            out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa)
         elif ar_len <= 0:
-            out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
+            out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
         else:
             out_ar = comfy.ops.scaled_dot_product_attention(
                 q[:, :, :ar_len], k[:, :, :ar_len], v[:, :, :ar_len],
-                attn_mask=None, dropout_p=0.0, is_causal=True,
+                attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa,
             )
             out_gen = optimized_attention(
                 q[:, :, ar_len:], k, v, heads,
                 mask=None, skip_reshape=True, skip_output_reshape=True,
-                transformer_options=transformer_options,
+                transformer_options=transformer_options, enable_gqa=enable_gqa,
             )
             out = torch.cat([out_ar, out_gen], dim=2)
 

comfy_api/latest/_input_impl/video_types.py

@@ -1,5 +1,6 @@
 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
@@ -9,6 +10,7 @@ import itertools
 import json
 import numpy as np
 import math
+import os
 import torch
 from .._util import VideoContainer, VideoCodec, VideoComponents
 import logging
@@ -58,6 +60,57 @@ 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:
+            frames = ()
+        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: dict | None):
+    """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.
@@ -192,13 +245,10 @@ class VideoFromFile(VideoInput):
                     return estimated_frames
 
             # 3. Last resort: decode frames and count them (streaming)
-            if self.__start_time < 0:
+            start_time, duration = self.get_active_trim_window()
-                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 + self.__duration) / video_stream.time_base)
+            end_pts = int((start_time + duration) / video_stream.time_base)
             container.seek(start_pts, stream=video_stream)
             frame_iterator = (
                 container.decode(video_stream)
@@ -253,17 +303,14 @@ class VideoFromFile(VideoInput):
 
     def get_components_internal(self, container: InputContainer) -> VideoComponents:
         video_stream = self._get_first_video_stream(container)
-        if self.__start_time < 0:
+        start_time, duration = self.get_active_trim_window()
-            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)
+        end_pts = int((start_time + duration) / video_stream.time_base)
 
         if start_pts != 0:
             container.seek(start_pts, stream=video_stream)
@@ -281,18 +328,11 @@ class VideoFromFile(VideoInput):
         video_done = False
         audio_done = True
 
-        # Use the last decodable audio stream. Streams FFmpeg has no decoder for have no codec context,
+        audio_stream = last_decodable_audio_stream(container)
-        # and decoding their packets crashes the process. (e.g. APAC spatial-audio track in iPhone)
-        audio_stream = next(
-            (s for s in reversed(container.streams.audio) if s.codec_context is not None),
-            None,
-        )
         if audio_stream is not None:
             streams += [audio_stream]
             resampler = av.audio.resampler.AudioResampler(format='fltp')
             audio_done = False
-        elif len(container.streams.audio):
-            logging.warning("No decodable audio stream found in video; ignoring audio.")
 
         for packet in container.demux(*streams):
             if video_done and audio_done:
@@ -305,7 +345,7 @@ class VideoFromFile(VideoInput):
                     for frame in packet.decode():
                         if frame.pts < start_pts:
                             continue
-                        if self.__duration and frame.pts >= end_pts:
+                        if duration and frame.pts >= end_pts:
                             video_done = True
                             break
 
@@ -372,7 +412,7 @@ class VideoFromFile(VideoInput):
                     map(resampler.resample, packet.decode())
                 )
                 for frame in aframes:
-                    if self.__duration and frame.time > start_time + self.__duration:
+                    if duration and frame.time > start_time + duration:
                         audio_done = True
                         break
 
@@ -394,8 +434,8 @@ class VideoFromFile(VideoInput):
 
         if len(audio_frames) > 0:
             audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
-            if self.__duration:
+            if duration:
-                audio_data = audio_data[..., :int(self.__duration * audio_stream.sample_rate)]
+                audio_data = audio_data[..., :int(duration * audio_stream.sample_rate)]
 
             audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
             audio = AudioInput({
@@ -441,28 +481,14 @@ class VideoFromFile(VideoInput):
             if not reuse_streams:
                 if bit_depth is None:
                     bit_depth = source_bit_depth
-                components = self.get_components_internal(container)
+                return self._save_transcoded(container, path, format=format, codec=codec, metadata=metadata, bit_depth=bit_depth)
-                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:
-                # Copy over the original metadata
+                # Add metadata before writing any streams
-                for key, value in container.metadata.items():
+                write_output_metadata(container, output_container, metadata)
-                    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. Streams with no codec context cannot be used as an output template.
                 stream_map = {}
@@ -480,6 +506,282 @@ 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: dict | None,
+        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
+        stream_end_pts = None
+        if video_stream.duration is not None:
+            stream_end_pts = (video_stream.start_time or 0) + video_stream.duration
+        output_end_pts = end_pts
+        if stream_end_pts is not None and (output_end_pts is None or stream_end_pts < output_end_pts):
+            output_end_pts = stream_end_pts
+        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
+        last_video_end = None
+        # rebased pts -> true display duration: the mp4 muxer pads the last sample with 1/rate otherwise
+        video_frame_durations = {}
+        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
+            nonlocal samples_written, audio_done
+            if last_video_end is None:
+                cap = 0
+            else:
+                cap = math.ceil(last_video_end * 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
+                            if last_video_pts is not None:
+                                # the source continues past the window: hold the last kept frame to the window end
+                                end_offset = video_pts_offset if video_pts_offset is not None else start_pts
+                                last_video_end = max(last_video_end, end_pts - end_offset)
+                            break
+                        # the source's true display duration of this frame; average_rate is not a
+                        # frame duration (sparse/VFR sources), so it is only the fallback
+                        frame_duration = frame.duration if frame.duration else pts_step
+                        if end_pts is not None and frame.pts is not None:
+                            frame_duration = min(frame_duration, end_pts - frame.pts)
+                        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)
+                            # no B-frames: reordering makes mp4 sample durations follow decode order,
+                            # so irregular-VFR spans and trim windows land wrong
+                            out_video.codec_context.max_b_frames = 0
+                            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)
+                        frame_output_end = None
+                        if frame.pts is not None:
+                            if video_pts_offset is None:
+                                video_pts_offset = frame.pts
+                            frame.pts -= video_pts_offset
+                            if output_end_pts is not None:
+                                frame_output_end = output_end_pts - video_pts_offset
+                                if frame.pts + frame_duration > frame_output_end:
+                                    clamped_pts = frame_output_end - frame_duration
+                                    if clamped_pts >= 0 and (last_video_pts is None or clamped_pts > last_video_pts):
+                                        frame.pts = min(frame.pts, clamped_pts)
+                                    elif frame.pts < frame_output_end:
+                                        frame_duration = frame_output_end - frame.pts
+                                    else:
+                                        continue
+                        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
+                            if frame_output_end is not None and frame.pts + frame_duration > frame_output_end:
+                                if frame.pts >= frame_output_end:
+                                    continue
+                                frame_duration = frame_output_end - frame.pts
+                        last_video_pts = frame.pts
+                        last_video_end = frame.pts + frame_duration
+                        video_frame_durations[frame.pts] = frame_duration
+                        # 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
+                        for out_packet in out_video.encode(frame):
+                            out_packet.duration = video_frame_durations.pop(out_packet.pts, 0)
+                            output.mux(out_packet)
+                        drain_audio()
+
+                elif packet.stream == audio_stream and not audio_done:
+                    for resampled in itertools.chain.from_iterable(map(resampler.resample, packet.decode())):
+                        frame_start = None
+                        if resampled.pts is not None:
+                            # 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)
+                            if duration and not audio_started and frame_start >= start_time + duration:
+                                audio_done = True
+                                break
+                        if not audio_started:
+                            if frame_start is None:
+                                frame_start = 0.0
+                            to_skip = max(0, int((start_time - frame_start) * sample_rate))
+                            if to_skip >= resampled.samples:
+                                continue
+                            audio_started = True
+                            if duration and frame_start > start_time:
+                                duration_cap = min(duration_cap, math.ceil((start_time + duration - frame_start) * sample_rate))
+                            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)
+            window_fill = last_video_end - last_video_pts if video_done and last_video_pts is not None else 0
+            for out_packet in out_video.encode(None):
+                duration = video_frame_durations.pop(out_packet.pts, 0)
+                if out_packet.pts == last_video_pts:
+                    duration = max(duration, window_fill)
+                out_packet.duration = duration
+                output.mux(out_packet)
+            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]
@@ -527,22 +829,12 @@ class VideoFromComponents(VideoInput):
         bit_depth: int | None = None,
     ):
         """Save the video to a file path or BytesIO buffer."""
-        if format != VideoContainer.AUTO and format != VideoContainer.MP4:
+        open_kwargs = mp4_output_open_kwargs(path, format, codec)
-            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
-        extra_kwargs = {}
+        with av.open(path, **open_kwargs) as output:
-        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/apis/sync_so.py

@@ -0,0 +1,49 @@
+from pydantic import BaseModel, Field
+
+
+class SyncInputItem(BaseModel):
+    type: str = Field(..., description="Input kind: 'video', 'image' or 'audio'.")
+    url: str = Field(...)
+
+
+class SyncActiveSpeakerDetection(BaseModel):
+    auto_detect: bool | None = Field(
+        None, description="Detect the active speaker automatically. Video input only; rejected for images."
+    )
+    frame_number: int | None = Field(
+        None, description="Frame used for manual speaker selection. Must be 0 for image inputs."
+    )
+    coordinates: list[int] | None = Field(
+        None, description="Pixel [x, y] of the speaker's face in the frame selected by frame_number."
+    )
+
+
+class SyncGenerationOptions(BaseModel):
+    sync_mode: str | None = Field(
+        None,
+        description="How to resolve an audio/video duration mismatch: "
+        "cut_off, bounce, loop, silence or remap. Ignored for image inputs.",
+    )
+    i2v_prompt: str | None = Field(
+        None, description="Motion prompt for image-to-video generation. Image input only."
+    )
+    active_speaker_detection: SyncActiveSpeakerDetection | None = Field(None)
+
+
+class SyncGenerationRequest(BaseModel):
+    model: str = Field(..., description="Generation model, e.g. 'sync-3'.")
+    input: list[SyncInputItem] = Field(
+        ..., description="Exactly one visual input (video or image) plus one audio input."
+    )
+    options: SyncGenerationOptions | None = Field(None)
+
+
+class SyncGeneration(BaseModel):
+    """Subset of the Generation object returned by POST /v2/generate and GET /v2/generate/{id}."""
+
+    id: str = Field(...)
+    status: str = Field(..., description="PENDING | PROCESSING | COMPLETED | FAILED | REJECTED")
+    outputUrl: str | None = Field(None)
+    outputDuration: float | None = Field(None)
+    error: str | None = Field(None, description="Human-readable failure message.")
+    errorCode: str | None = Field(None, description="Stable machine-readable code from the GET /v2/errors catalog.")

comfy_api_nodes/nodes_sync_so.py

@@ -0,0 +1,391 @@
+from typing_extensions import override
+
+from comfy_api.latest import IO, ComfyExtension, Input
+from comfy_api_nodes.apis.sync_so import (
+    SyncActiveSpeakerDetection,
+    SyncGeneration,
+    SyncGenerationOptions,
+    SyncGenerationRequest,
+    SyncInputItem,
+)
+from comfy_api_nodes.util import (
+    ApiEndpoint,
+    download_url_to_video_output,
+    downscale_image_tensor,
+    downscale_image_tensor_by_max_side,
+    get_image_dimensions,
+    get_number_of_images,
+    poll_op,
+    sync_op,
+    upload_audio_to_comfyapi,
+    upload_image_to_comfyapi,
+    upload_video_to_comfyapi,
+    validate_audio_duration,
+)
+
+
+class SyncLipSyncNode(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="SyncLipSyncNode",
+            display_name="sync.so Lip Sync",
+            category="partner/video/sync.so",
+            description=(
+                "Re-sync mouth movement in a video to new speech audio using sync.so. "
+                "Handles close-ups, profiles and obstructions automatically while preserving "
+                "the speaker's expression. Cost scales with output duration."
+            ),
+            inputs=[
+                IO.Video.Input(
+                    "video",
+                    tooltip="Footage of the speaker to re-sync. Up to 4K (4096x2160); "
+                    "a constant frame rate of 24/25/30 fps works best.",
+                ),
+                IO.Audio.Input(
+                    "audio",
+                    tooltip="Speech audio to sync the mouth to.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=42,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "sync-3",
+                            [
+                                IO.Combo.Input(
+                                    "sync_mode",
+                                    options=["bounce", "cut_off", "loop", "silence", "remap"],
+                                    default="bounce",
+                                    tooltip=(
+                                        "How to handle a duration mismatch between video and audio; "
+                                        "this also sets the output length. "
+                                        "bounce: video plays forward then backward until the audio ends "
+                                        "(output = audio length). "
+                                        "loop: video restarts until the audio ends (output = audio length). "
+                                        "remap: video is time-stretched to match the audio (output = audio length). "
+                                        "cut_off: the longer track is trimmed (output = shorter length). "
+                                        "silence: nothing is trimmed; the shorter track is padded "
+                                        "(output = longer length)."
+                                    ),
+                                ),
+                                IO.Combo.Input(
+                                    "speaker_selection",
+                                    options=["default", "auto-detect", "coordinates"],
+                                    default="default",
+                                    tooltip=(
+                                        "Which face to lipsync when several people are visible. "
+                                        "default: let the model decide. "
+                                        "auto-detect: detect and follow the active speaker. "
+                                        "coordinates: target the face at pixel (speaker_x, speaker_y) "
+                                        "in the frame chosen by speaker_frame."
+                                    ),
+                                ),
+                                IO.Int.Input(
+                                    "speaker_frame",
+                                    default=0,
+                                    min=0,
+                                    max=1_000_000,
+                                    advanced=True,
+                                    tooltip="Video frame used to locate the speaker. "
+                                    "Only used when speaker_selection is 'coordinates'.",
+                                ),
+                                IO.Int.Input(
+                                    "speaker_x",
+                                    default=0,
+                                    min=0,
+                                    max=4096,
+                                    advanced=True,
+                                    tooltip="X pixel coordinate of the speaker's face. "
+                                    "Only used when speaker_selection is 'coordinates'.",
+                                ),
+                                IO.Int.Input(
+                                    "speaker_y",
+                                    default=0,
+                                    min=0,
+                                    max=4096,
+                                    advanced=True,
+                                    tooltip="Y pixel coordinate of the speaker's face. "
+                                    "Only used when speaker_selection is 'coordinates'.",
+                                ),
+                            ],
+                        )
+                    ],
+                    tooltip="sync.so generation model.",
+                ),
+            ],
+            outputs=[IO.Video.Output()],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd":0.19019,"format":{"approximate":true,"suffix":"/second"}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        video: Input.Video,
+        audio: Input.Audio,
+        seed: int,
+        model: dict,
+    ) -> IO.NodeOutput:
+        try:
+            width, height = video.get_dimensions()
+        except Exception:
+            width = height = None
+        if width and height and (max(width, height) > 4096 or width * height > 4096 * 2160):
+            raise ValueError(
+                f"sync.so rejects videos above 4K (4096x2160); got {width}x{height}. Downscale the video first."
+            )
+        validate_audio_duration(audio, max_duration=600)
+
+        if model["speaker_selection"] == "auto-detect":
+            speaker_detection = SyncActiveSpeakerDetection(auto_detect=True)
+        elif model["speaker_selection"] == "coordinates":
+            speaker_detection = SyncActiveSpeakerDetection(
+                frame_number=model["speaker_frame"],
+                coordinates=[model["speaker_x"], model["speaker_y"]],
+            )
+        else:
+            speaker_detection = None
+
+        video_url = await upload_video_to_comfyapi(cls, video, max_duration=600)
+        audio_url = await upload_audio_to_comfyapi(cls, audio)
+
+        generation = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/synclabs/v2/generate", method="POST"),
+            response_model=SyncGeneration,
+            data=SyncGenerationRequest(
+                model=model["model"],
+                input=[
+                    SyncInputItem(type="video", url=video_url),
+                    SyncInputItem(type="audio", url=audio_url),
+                ],
+                options=SyncGenerationOptions(
+                    sync_mode=model["sync_mode"],
+                    active_speaker_detection=speaker_detection,
+                ),
+            ),
+        )
+        generation = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/synclabs/v2/generate/{generation.id}"),
+            response_model=SyncGeneration,
+            status_extractor=lambda g: g.status,
+            completed_statuses=["COMPLETED", "FAILED", "REJECTED"],
+            failed_statuses=[],
+            queued_statuses=["PENDING"],
+            poll_interval=10.0,
+        )
+        if generation.status != "COMPLETED":
+            code = f" [{generation.errorCode}]" if generation.errorCode else ""
+            raise ValueError(
+                f"sync.so generation {generation.status.lower()}{code}: "
+                f"{generation.error or 'no error details provided'}"
+            )
+        if not generation.outputUrl:
+            raise ValueError("sync.so generation completed but no output URL was returned.")
+        return IO.NodeOutput(await download_url_to_video_output(generation.outputUrl))
+
+
+class SyncTalkingImageNode(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="SyncTalkingImageNode",
+            display_name="sync.so Talking Image",
+            category="partner/video/sync.so",
+            description=(
+                "Animate a still portrait into a talking video driven by speech audio, "
+                "using sync.so's sync-3 model. The output duration matches the audio. "
+                "Cost scales with output duration."
+            ),
+            inputs=[
+                IO.Image.Input(
+                    "image",
+                    tooltip="A single image with a clearly visible face, up to 4K (4096x2160).",
+                ),
+                IO.Audio.Input(
+                    "audio",
+                    tooltip="Speech audio driving the talking video; the output duration matches it. "
+                    "Chain any TTS node here to drive the animation from text.",
+                ),
+                IO.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Optional guidance for how the portrait comes to life, e.g. "
+                    "'make the subject smile and look at the camera'. "
+                    "Leave empty for natural talking motion.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+                IO.DynamicCombo.Input(
+                    "model",
+                    options=[
+                        IO.DynamicCombo.Option(
+                            "sync-3",
+                            [
+                                IO.Combo.Input(
+                                    "speaker_selection",
+                                    options=["default", "coordinates"],
+                                    default="default",
+                                    tooltip=(
+                                        "Which face to animate when several people are visible. "
+                                        "default: let the model decide. "
+                                        "coordinates: target the face at pixel (speaker_x, speaker_y) "
+                                        "in the image. Auto-detection is not supported for images."
+                                    ),
+                                ),
+                                IO.Int.Input(
+                                    "speaker_x",
+                                    default=0,
+                                    min=0,
+                                    max=4096,
+                                    advanced=True,
+                                    tooltip="X pixel coordinate of the speaker's face. "
+                                    "Only used when speaker_selection is 'coordinates'.",
+                                ),
+                                IO.Int.Input(
+                                    "speaker_y",
+                                    default=0,
+                                    min=0,
+                                    max=4096,
+                                    advanced=True,
+                                    tooltip="Y pixel coordinate of the speaker's face. "
+                                    "Only used when speaker_selection is 'coordinates'.",
+                                ),
+                                IO.Boolean.Input(
+                                    "auto_downscale",
+                                    default=True,
+                                    advanced=True,
+                                    tooltip="Automatically downscale the image if it exceeds the 4K "
+                                    "(4096x2160) input limit; speaker coordinates are scaled to match. "
+                                    "When disabled, an oversized image raises an error instead.",
+                                ),
+                            ],
+                        )
+                    ],
+                    tooltip="sync.so generation model. Image input is exclusive to sync-3.",
+                ),
+            ],
+            outputs=[IO.Video.Output()],
+            hidden=[
+                IO.Hidden.auth_token_comfy_org,
+                IO.Hidden.api_key_comfy_org,
+                IO.Hidden.unique_id,
+            ],
+            is_api_node=True,
+            price_badge=IO.PriceBadge(
+                expr="""{"type":"usd","usd":0.19019,"format":{"approximate":true,"suffix":"/second"}}""",
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        image: Input.Image,
+        audio: Input.Audio,
+        prompt: str,
+        seed: int,
+        model: dict,
+    ) -> IO.NodeOutput:
+        if get_number_of_images(image) != 1:
+            raise ValueError("Exactly one image is required; got a batch. Pick one frame first.")
+        validate_audio_duration(audio, max_duration=600)
+
+        height, width = get_image_dimensions(image)
+        speaker_x, speaker_y = model["speaker_x"], model["speaker_y"]
+        if max(width, height) > 4096 or width * height > 4096 * 2160:
+            if not model["auto_downscale"]:
+                raise ValueError(
+                    f"sync.so rejects images above 4K (4096x2160); got {width}x{height}. "
+                    "Downscale the image first or enable auto_downscale."
+                )
+            image = downscale_image_tensor(image, total_pixels=4096 * 2160)
+            image = downscale_image_tensor_by_max_side(image, max_side=4096)
+            new_height, new_width = get_image_dimensions(image)
+            # speaker coordinates are given in the original image's pixel space
+            speaker_x = min(new_width - 1, round(speaker_x * new_width / width))
+            speaker_y = min(new_height - 1, round(speaker_y * new_height / height))
+
+        if model["speaker_selection"] == "coordinates":
+            speaker_detection = SyncActiveSpeakerDetection(
+                frame_number=0,  # images have a single frame; auto_detect is rejected by the API
+                coordinates=[speaker_x, speaker_y],
+            )
+        else:
+            speaker_detection = None
+
+        image_url = await upload_image_to_comfyapi(cls, image, mime_type="image/png", total_pixels=None)
+        audio_url = await upload_audio_to_comfyapi(cls, audio)
+
+        generation = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/synclabs/v2/generate", method="POST"),
+            response_model=SyncGeneration,
+            data=SyncGenerationRequest(
+                model=model["model"],
+                input=[
+                    SyncInputItem(type="image", url=image_url),
+                    SyncInputItem(type="audio", url=audio_url),
+                ],
+                options=SyncGenerationOptions(
+                    i2v_prompt=prompt.strip() or None,
+                    active_speaker_detection=speaker_detection,
+                ),
+            ),
+        )
+        generation = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/synclabs/v2/generate/{generation.id}"),
+            response_model=SyncGeneration,
+            status_extractor=lambda g: g.status,
+            completed_statuses=["COMPLETED", "FAILED", "REJECTED"],
+            failed_statuses=[],
+            queued_statuses=["PENDING"],
+            poll_interval=10.0,
+        )
+        if generation.status != "COMPLETED":
+            code = f" [{generation.errorCode}]" if generation.errorCode else ""
+            raise ValueError(
+                f"sync.so generation {generation.status.lower()}{code}: "
+                f"{generation.error or 'no error details provided'}"
+            )
+        if not generation.outputUrl:
+            raise ValueError("sync.so generation completed but no output URL was returned.")
+        return IO.NodeOutput(await download_url_to_video_output(generation.outputUrl))
+
+
+class SyncExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[IO.ComfyNode]]:
+        return [
+            SyncLipSyncNode,
+            SyncTalkingImageNode,
+        ]
+
+
+async def comfy_entrypoint() -> SyncExtension:
+    return SyncExtension()

comfy_api_nodes/util/_helpers.py

@@ -15,6 +15,7 @@ from comfy.comfy_api_env import normalize_comfy_api_base
 from comfy.deploy_environment import get_deploy_environment
 from comfy.model_management import processing_interrupted
 from comfy_api.latest import IO
+from comfy_execution.utils import get_executing_context
 from comfyui_version import __version__ as comfyui_version
 
 from .common_exceptions import ProcessingInterrupted
@@ -57,12 +58,16 @@ def get_comfy_api_headers(node_cls: type[IO.ComfyNode]) -> dict[str, str]:
     relative/cloud URLs resolved against ``default_base_url()``; because the result
     includes auth, callers must not attach it to arbitrary absolute/presigned URLs.
     """
-    return {
+    headers = {
         **get_auth_header(node_cls),
         "Comfy-Env": get_deploy_environment(),
         "Comfy-Usage-Source": get_usage_source(node_cls),
         "Comfy-Core-Version": comfyui_version,
     }
+    ctx = get_executing_context()
+    if ctx is not None:
+        headers["Comfy-Job-Id"] = ctx.prompt_id
+    return headers
 
 
 def default_base_url() -> str:

comfy_extras/nodes_load_3d.py

@@ -174,8 +174,9 @@ class Preview3DAdvanced(IO.ComfyNode):
         filename = f"preview3d_advanced_{uuid.uuid4().hex}.{model_3d.format}"
         model_3d.save_to(os.path.join(folder_paths.get_temp_directory(), filename))
 
+        viewport_state = viewport_state if isinstance(viewport_state, dict) else {}
         camera_info_input = kwargs.get("camera_info", None)
-        camera_info = camera_info_input if camera_info_input is not None else viewport_state['camera_info']
+        camera_info = camera_info_input if camera_info_input is not None else viewport_state.get('camera_info')
         model_3d_info_input = kwargs.get("model_3d_info", None)
         model_3d_info = model_3d_info_input if model_3d_info_input is not None else viewport_state.get('model_3d_info', [])
         return IO.NodeOutput(
@@ -243,8 +244,9 @@ class PreviewGaussianSplat(IO.ComfyNode):
         filename = f"preview_splat_{uuid.uuid4().hex}.{model_3d.format}"
         model_3d.save_to(os.path.join(folder_paths.get_temp_directory(), filename))
 
+        viewport_state = viewport_state if isinstance(viewport_state, dict) else {}
         camera_info_input = kwargs.get("camera_info", None)
-        camera_info = camera_info_input if camera_info_input is not None else viewport_state['camera_info']
+        camera_info = camera_info_input if camera_info_input is not None else viewport_state.get('camera_info')
         model_3d_info_input = kwargs.get("model_3d_info", None)
         model_3d_info = model_3d_info_input if model_3d_info_input is not None else viewport_state.get('model_3d_info', [])
         return IO.NodeOutput(
@@ -303,8 +305,9 @@ class PreviewPointCloud(IO.ComfyNode):
         filename = f"preview_pointcloud_{uuid.uuid4().hex}.{model_3d.format}"
         model_3d.save_to(os.path.join(folder_paths.get_temp_directory(), filename))
 
+        viewport_state = viewport_state if isinstance(viewport_state, dict) else {}
         camera_info_input = kwargs.get("camera_info", None)
-        camera_info = camera_info_input if camera_info_input is not None else viewport_state['camera_info']
+        camera_info = camera_info_input if camera_info_input is not None else viewport_state.get('camera_info')
         model_3d_info_input = kwargs.get("model_3d_info", None)
         model_3d_info = model_3d_info_input if model_3d_info_input is not None else viewport_state.get('model_3d_info', [])
         return IO.NodeOutput(
@@ -375,8 +378,9 @@ class Load3DAdvanced(IO.ComfyNode):
         file_3d = None
         if model_file and model_file != "none":
             file_3d = Types.File3D(folder_paths.get_annotated_filepath(model_file))
+        viewport_state = viewport_state if isinstance(viewport_state, dict) else {}
         model_3d_info = viewport_state.get('model_3d_info', [])
-        return IO.NodeOutput(file_3d, model_3d_info, viewport_state['camera_info'], width, height)
+        return IO.NodeOutput(file_3d, model_3d_info, viewport_state.get('camera_info'), width, height)
 
 
 class Load3DExtension(ComfyExtension):

comfy_extras/nodes_save_3d.py

@@ -418,8 +418,9 @@ def _save_file3d_to_output(model_3d: Types.File3D, filename_prefix: str) -> str:
 
 def execute_save_3d_advanced(model_3d, viewport_state, width, height, filename_prefix, kwargs) -> IO.NodeOutput:
     model_file = _save_file3d_to_output(model_3d, filename_prefix)
+    viewport_state = viewport_state if isinstance(viewport_state, dict) else {}
     camera_info_input = kwargs.get("camera_info", None)
-    camera_info = camera_info_input if camera_info_input is not None else viewport_state['camera_info']
+    camera_info = camera_info_input if camera_info_input is not None else viewport_state.get('camera_info')
     model_3d_info_input = kwargs.get("model_3d_info", None)
     model_3d_info = model_3d_info_input if model_3d_info_input is not None else viewport_state.get('model_3d_info', [])
     return IO.NodeOutput(

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.27.0"
+__version__ = "0.28.0"

execution.py

@@ -426,12 +426,12 @@ def _is_intermediate_output(dynprompt, node_id):
 
 
 def _send_cached_ui(server, node_id, display_node_id, cached, prompt_id, ui_outputs):
+    if cached.ui is not None:
+        ui_outputs[node_id] = cached.ui
     if server.client_id is None:
         return
     cached_ui = cached.ui or {}
     server.send_sync("executed", { "node": node_id, "display_node": display_node_id, "output": cached_ui.get("output", None), "prompt_id": prompt_id }, server.client_id)
-    if cached.ui is not None:
-        ui_outputs[node_id] = cached.ui
 
 async def execute(server, dynprompt, caches, current_item, extra_data, executed, prompt_id, execution_list, pending_subgraph_results, pending_async_nodes, ui_outputs):
     unique_id = current_item

openapi.yaml

@@ -7,18 +7,18 @@ components:
                     description: Timestamp when the asset was created
                     format: date-time
                     type: string
+                display_name:
+                    description: Display name of the asset. Mirrors name for backwards compatibility.
+                    nullable: true
+                    type: string
+                file_path:
+                    description: Relative path in global-namespace-root form (e.g. "models/checkpoints/flux.safetensors")
+                    nullable: true
+                    type: string
                 hash:
                     description: Blake3 hash of the asset content.
                     pattern: ^blake3:[a-f0-9]{64}$
                     type: string
-                loader_path:
-                    description: The value a loader consumes to load this asset. Null when no loader can resolve the file.
-                    nullable: true
-                    type: string
-                display_name:
-                    description: Human-facing label for the asset. Not unique.
-                    nullable: true
-                    type: string
                 id:
                     description: Unique identifier for the asset
                     format: uuid
@@ -144,6 +144,14 @@ components:
         AssetUpdated:
             description: Response returned when an existing asset is successfully updated.
             properties:
+                display_name:
+                    description: Display name of the asset. Mirrors name for backwards compatibility.
+                    nullable: true
+                    type: string
+                file_path:
+                    description: Relative path in global-namespace-root form (e.g. "models/checkpoints/flux.safetensors")
+                    nullable: true
+                    type: string
                 hash:
                     description: Blake3 hash of the asset content.
                     pattern: ^blake3:[a-f0-9]{64}$
@@ -775,14 +783,6 @@ components:
         ModelFolder:
             description: Represents a folder containing models
             properties:
-                extensions:
-                    description: The folder's registered file-extension allowlist. An empty array means the folder accepts any extension (match-all).
-                    example:
-                        - .ckpt
-                        - .safetensors
-                    items:
-                        type: string
-                    type: array
                 folders:
                     description: List of paths where models of this type are stored
                     example:
@@ -1644,7 +1644,7 @@ paths:
                                     format: uuid
                                     type: string
                                 tags:
-                                    description: JSON-encoded array of tag strings. For new byte uploads, include exactly one destination role (`input`, `output`, or `models`); `models` uploads also require exactly one `model_type:<folder_name>` tag. Extra tags are stored as labels and do not create path components.
+                                    description: JSON-encoded array of freeform tag strings, e.g. '["models","checkpoint"]'. Common types include "models", "input", "output", and "temp", but any tag can be used in any order.
                                     type: string
                                 user_metadata:
                                     description: Custom JSON metadata as a string
@@ -1829,7 +1829,7 @@ paths:
                     content:
                         application/json:
                             schema:
-                                $ref: '#/components/schemas/Asset'
+                                $ref: '#/components/schemas/AssetUpdated'
                     description: Asset updated successfully
                 "400":
                     content:
@@ -2470,9 +2470,6 @@ paths:
                                     supports_preview_metadata:
                                         description: Whether the server supports preview metadata
                                         type: boolean
-                                    supports_model_type_tags:
-                                        description: Whether the server supports namespaced model type asset tags
-                                        type: boolean
                                 type: object
                     description: Success
                     headers:
@@ -3300,6 +3297,12 @@ paths:
                             schema:
                                 $ref: '#/components/schemas/ErrorResponse'
                     description: Invalid request parameters
+                "401":
+                    content:
+                        application/json:
+                            schema:
+                                $ref: '#/components/schemas/ErrorResponse'
+                    description: Unauthorized - Authentication required
                 "500":
                     content:
                         application/json:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.27.0"
+version = "0.28.0"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.10"

requirements.txt

@@ -1,6 +1,6 @@
-comfyui-frontend-package==1.45.20
+comfyui-frontend-package==1.45.21
-comfyui-workflow-templates==0.11.6
+comfyui-workflow-templates==0.11.9
-comfyui-embedded-docs==0.5.7
+comfyui-embedded-docs==0.5.8
 torch
 torchsde
 torchvision
@@ -22,7 +22,7 @@ alembic
 SQLAlchemy>=2.0.0
 filelock
 av>=16.0.0
-comfy-kitchen==0.2.18
+comfy-kitchen==0.2.20
 comfy-aimdo==0.4.10
 requests
 simpleeval>=1.0.0

tests-unit/comfy_api_test/video_types_test.py

@@ -2,11 +2,12 @@ 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
+from comfy_api.util.video_types import VideoComponents, VideoContainer, VideoCodec
 from comfy_api.input.basic_types import AudioInput
 from av.error import InvalidDataError
 
@@ -237,3 +238,526 @@ 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)
+
+    buffer.seek(0)
+    trimmed_before_audio = transcode_and_probe(VideoFromFile(buffer, duration=1))
+    assert trimmed_before_audio["frames"] == fps
+    assert trimmed_before_audio["audio_codecs"] == []
+    assert trimmed_before_audio["audio_seconds"] is None
+
+    buffer.seek(0)
+    trimmed_crossing_audio = transcode_and_probe(VideoFromFile(buffer, start_time=11.5, duration=1))
+    assert trimmed_crossing_audio["frames"] == fps
+    assert trimmed_crossing_audio["audio_codecs"] == ["aac"]
+    assert trimmed_crossing_audio["video_seconds"] == pytest.approx(1.0, abs=0.05)
+    assert trimmed_crossing_audio["audio_seconds"] == pytest.approx(0.5, 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_sparse_video_keeps_true_duration():
+    """average_rate is not a frame duration: a 3-frame video spanning 60 s averages
+    0.05 fps, and padding the last frame with 1/average_rate used to extend the
+    output — and the audio kept with it — about 20 s past the source span."""
+    sample_rate = 48000
+    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=sample_rate, layout="mono")
+        for i, second in enumerate((0, 30, 60)):
+            frame = av.VideoFrame.from_ndarray(
+                torch.full((64, 64, 3), i * 80, dtype=torch.uint8).numpy(), format="rgb24"
+            ).reformat(format="yuv420p")
+            frame.pts = second * 30
+            frame.time_base = Fraction(1, 30)
+            container.mux(video_stream.encode(frame))
+        for offset in range(0, 90 * sample_rate, 1024):
+            n = min(1024, 90 * 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 = offset
+            container.mux(audio_stream.encode(audio_frame))
+        for stream in (video_stream, audio_stream):
+            container.mux(stream.encode(None))
+
+    result = transcode_and_probe(VideoFromFile(buffer))
+    assert result["frames"] == 3
+    # the last frame keeps its true stts duration (1/30 s), not 1/average_rate (~20 s)
+    assert result["video_seconds"] == pytest.approx(60.03, abs=0.05)
+    assert result["audio_seconds"] == pytest.approx(60.03, abs=0.1)
+
+    trimmed = transcode_and_probe(VideoFromFile(buffer, duration=45))
+    assert trimmed["frames"] == 2
+    # a kept frame whose source duration crosses the window end is clamped to it
+    assert trimmed["video_seconds"] == pytest.approx(45.0, abs=0.05)
+    assert trimmed["audio_seconds"] == pytest.approx(45.0, abs=0.1)
+
+
+def test_save_to_transcode_clamps_final_pts_to_declared_stream_duration():
+    """Some iPhone MOVs report a video stream duration that ends before the final
+    decoded frame's nominal duration. A transcode must not turn that trailing
+    timestamp quirk into an extra frame interval compared to the source/remux path."""
+    fps = 30
+    buffer = io.BytesIO()
+    with av.open(buffer, mode="w", format="mp4") as container:
+        video_stream = container.add_stream("mpeg4", rate=fps)
+        video_stream.width = video_stream.height = 64
+        video_stream.pix_fmt = "yuv420p"
+        for i, pts in enumerate([*range(31), 32]):
+            frame = av.VideoFrame.from_ndarray(
+                torch.full((64, 64, 3), (i * 7) % 256, dtype=torch.uint8).numpy(), format="rgb24"
+            ).reformat(format="yuv420p")
+            frame.pts = pts
+            frame.time_base = Fraction(1, fps)
+            container.mux(video_stream.encode(frame))
+        container.mux(video_stream.encode(None))
+
+    class _StreamProxy:
+        def __init__(self, stream, duration):
+            self._stream = stream
+            self.duration = duration
+
+        def __getattr__(self, name):
+            return getattr(self._stream, name)
+
+    class _StreamsProxy:
+        def __init__(self, video_stream):
+            self.video = [video_stream]
+            self.audio = []
+
+    class _PacketProxy:
+        def __init__(self, packet, stream):
+            self._packet = packet
+            self.stream = stream
+
+        def __getattr__(self, name):
+            return getattr(self._packet, name)
+
+    class _ContainerProxy:
+        def __init__(self, container, stream):
+            self._container = container
+            self._stream = stream
+            self.streams = _StreamsProxy(stream)
+
+        def __getattr__(self, name):
+            return getattr(self._container, name)
+
+        def demux(self, *streams):
+            for packet in self._container.demux(self._stream._stream):
+                yield _PacketProxy(packet, self._stream)
+
+    buffer.seek(0)
+    output = io.BytesIO()
+    with av.open(buffer) as container:
+        real_stream = container.streams.video[0]
+        declared_duration = 32 * int(round((1 / fps) / real_stream.time_base))
+        stream = _StreamProxy(real_stream, declared_duration)
+        VideoFromFile(buffer)._save_transcoded(
+            _ContainerProxy(container, stream), output, VideoContainer.MP4, VideoCodec.H264, None, 8
+        )
+
+    output.seek(0)
+    with av.open(output) as container:
+        video_stream = container.streams.video[0]
+        frames = [f for p in container.demux(video_stream) for f in p.decode()]
+        assert len(frames) == 32
+        assert float(video_stream.duration * video_stream.time_base) == pytest.approx(32 / fps, abs=0.01)
+        assert float(frames[-1].pts * frames[-1].time_base) == pytest.approx(31 / fps, abs=0.01)
+
+
+def test_save_to_transcode_irregular_vfr_keeps_span():
+    """B-frames reorder packets, and mp4 sample durations follow decode order: the dts
+    timeline ends before the pts timeline, so an irregular-VFR source's tail holds fell
+    out of the container (this 20.23 s span used to come out as 15.27 s, and the 10 s
+    trim as 6.03 s). The transcode encodes without B-frames so every sample keeps its
+    true display duration."""
+    durations = [1, 1, 60, 1, 1, 120, 1, 180, 1, 1, 150, 90]  # 1/30 s ticks, span 20.2333 s
+    generator = torch.Generator().manual_seed(7)
+    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"
+        pts = 0
+        for duration in durations:
+            # textured frames, so an encoder with default settings has B-frames to gain from
+            frame = av.VideoFrame.from_ndarray(
+                torch.randint(0, 255, (64, 64, 3), generator=generator, dtype=torch.uint8).numpy(),
+                format="rgb24",
+            ).reformat(format="yuv420p")
+            frame.pts = pts
+            frame.time_base = Fraction(1, 30)
+            pts += duration
+            for packet in video_stream.encode(frame):
+                packet.duration = duration  # exact stts in the source
+                container.mux(packet)
+        container.mux(video_stream.encode(None))
+
+    result = transcode_and_probe(VideoFromFile(buffer))
+    assert result["frames"] == len(durations)
+    assert result["video_seconds"] == pytest.approx(sum(durations) / 30, abs=0.05)
+
+    trimmed = transcode_and_probe(VideoFromFile(buffer, duration=10))
+    assert trimmed["frames"] == 8  # frames at 12.167 s+ fall outside the window
+    assert trimmed["video_seconds"] == pytest.approx(10.0, abs=0.05)
+
+
+def test_save_to_transcode_trim_survives_missing_leading_pts():
+    """A trim should survive pts-less kept frames followed by a real-pts frame past the window."""
+    nulled_frames = 0
+
+    class _PacketProxy:
+        def __init__(self, packet):
+            self._packet = packet
+
+        def __getattr__(self, name):
+            return getattr(self._packet, name)
+
+        @property
+        def stream(self):
+            return self._packet.stream
+
+        def decode(self):
+            nonlocal nulled_frames
+            frames = self._packet.decode()
+            for frame in frames:
+                if nulled_frames < 2:
+                    frame.pts = None
+                    nulled_frames += 1
+            return frames
+
+    class _ContainerProxy:
+        def __init__(self, real):
+            self._real = real
+
+        def __getattr__(self, name):
+            return getattr(self._real, name)
+
+        def demux(self, *streams):
+            for packet in self._real.demux(*streams):
+                yield _PacketProxy(packet)
+
+    file_path = create_transcode_source(frames=10, audio_streams=0)
+    try:
+        buffer = io.BytesIO()
+        with av.open(file_path) as container:
+            # 0.05 s window: both pts-less frames are kept (synthesized pts 0 and 512),
+            # and the first real-pts frame (1024 ticks) already lies past end_pts (768)
+            VideoFromFile(file_path, duration=0.05)._save_transcoded(
+                _ContainerProxy(container), buffer, VideoContainer.MP4, VideoCodec.H264, None, 8
+            )
+        assert nulled_frames == 2
+        buffer.seek(0)
+        with av.open(buffer) as container:
+            video_stream = container.streams.video[0]
+            frames = [f for p in container.demux(video_stream) for f in p.decode()]
+            assert len(frames) == 2
+            assert float(video_stream.duration * video_stream.time_base) == pytest.approx(2 / 30, abs=0.01)
+    finally:
+        os.unlink(file_path)
+
+
+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)

tests/execution/test_execution.py

@@ -818,6 +818,30 @@ class TestExecution:
         except urllib.error.HTTPError:
             pass  # Expected behavior
 
+    def test_cached_outputs_in_job_without_client_id(self, client: ComfyClient, builder: GraphBuilder):
+        g = builder
+        image = g.node("StubImage", content="BLACK", height=32, width=32, batch_size=1)
+        output = g.node("SaveImage", images=image.out(0))
+
+        # Prime the cache with a normal run.
+        client.run(g)
+
+        # Resubmit anonymously (no client_id) so output nodes are cache hits with no websocket client.
+        data = json.dumps({"prompt": g.finalize()}).encode('utf-8')
+        req = urllib.request.Request(f"http://{client.server_address}/prompt", data=data)
+        prompt_id = json.loads(urllib.request.urlopen(req).read())['prompt_id']
+
+        for _ in range(100):
+            job = client.get_job(prompt_id)
+            if job is not None and job['status'] not in ('pending', 'in_progress'):
+                break
+            time.sleep(0.1)
+        else:
+            raise AssertionError("Prompt did not complete in time")
+
+        assert job['status'] == 'completed'
+        assert output.id in job['outputs'], "Cached outputs must appear in job outputs without a client_id"
+
     def _create_history_item(self, client, builder):
         g = GraphBuilder(prefix="offset_test")
         input_node = g.node(