[Bugfix][MiniCPM-o] Bind omni-duplex video frames to the unit they close (#6404)

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>

examples/online_serving/minicpmo/README.md

@@ -159,6 +159,33 @@ python examples/online_serving/minicpmo/realtime_duplex_demo.py \
     --output-dir /tmp/minicpmo_realtime_duplex_demo
 ```
 
+Video input uses the same session. PyAV demuxes JPEG frames at `--video-fps`
+(default 1.0) and vLLM `load_audio` extracts a 16 kHz mono WAV unless
+`--input-wav` overrides the soundtrack. Frames keep their capture size
+(`--frame-max-side 0`); the server `process_image` normalizes at 448.
+
+`--stack-frames N` raises the visual refresh rate the way official duplex does:
+each 1 s unit also samples the `N-1` sub-frames captured inside it and tiles
+them into a single composite image sent next to that unit's base frame. The
+audio cadence never changes — a unit is always one second — and the wire always
+carries 2 images per unit however large `N` is, because the sub-frames share one
+composite. Official uses 5 for high refresh rate mode:
+
+```bash
+python examples/online_serving/minicpmo/realtime_duplex_demo.py \
+    --url ws://localhost:8099/v1/realtime?duplex=1 \
+    --model openbmb/MiniCPM-o-4_5 \
+    --input-video /path/to/clip.mp4 \
+    --stack-frames 5 \
+    --ref-audio /path/to/MiniCPM-o-Demo/assets/ref_audio/ref_minicpm_signature.wav \
+    --output-dir /tmp/minicpmo_realtime_duplex_video_demo
+```
+
+Detail inside a composite is capped by `scale_resolution=448` at
+`max_slice_nums=1`: official suggests HD slicing (`max_slice_nums=[2, 1]`) for
+stacked frames, which the duplex adapter does not implement yet. Reading small
+text or digits out of a wide scene is limited by that, not by frame timing.
+
 ## Open the experimental browser client
 
 The browser UI serves the page and proxies the same-origin Realtime WebSocket to

examples/online_serving/minicpmo/realtime_duplex_demo.py

@@ -12,7 +12,9 @@ from __future__ import annotations
 import argparse
 import asyncio
 import base64
+import io
 import json
+import math
 import sys
 import time
 from pathlib import Path
@@ -22,8 +24,8 @@ if str(REPO_ROOT) not in sys.path:
     sys.path.insert(0, str(REPO_ROOT))
 
 from vllm_omni.experimental.fullduplex.client import (  # noqa: E402
-    PCM16_BYTES_PER_SAMPLE,  # noqa: F401 - compatibility export
-    PCM16_SAMPLE_RATE,  # noqa: F401 - compatibility export
+    PCM16_BYTES_PER_SAMPLE,
+    PCM16_SAMPLE_RATE,
     RealtimeDuplexClient,
     RealtimeEventCollector,
     build_realtime_url,
@@ -38,6 +40,10 @@ from vllm_omni.experimental.fullduplex.client import (  # noqa: E402
 from vllm_omni.experimental.fullduplex.client import (  # noqa: E402
     reference_audio_data_url as _ref_audio_data_url,
 )
+from vllm_omni.experimental.fullduplex.video_stacking import (  # noqa: E402
+    concat_frames_b64,
+    unit_subframe_offsets,
+)
 
 
 class _StreamingOutputWriter:
@@ -159,14 +165,258 @@ def _event_count_after(
     return sum(event.get("type") == event_type for event in events[index + 1 :])
 
 
-async def run_demo(args: argparse.Namespace) -> dict[str, object]:
-    input_pcm16 = read_pcm16_wav(Path(args.input_wav))
-    if not input_pcm16:
-        raise ValueError("input WAV has no audio")
+def _probe_video_frames_and_fps(video_path: Path) -> tuple[int, float]:
+    """Frame count and average FPS via PyAV (same approach as Daily-Omni)."""
+    import av
 
+    with av.open(str(video_path)) as container:
+        stream = container.streams.video[0]
+        avg_fps = float(stream.average_rate) if stream.average_rate else 0.0
+        num_frames = stream.frames or 0
+        if num_frames <= 0:
+            duration: float | None = None
+            if stream.duration is not None and stream.time_base is not None:
+                duration = float(stream.duration * stream.time_base)
+            elif container.duration is not None:
+                duration = container.duration / av.time_base
+            if duration and avg_fps:
+                num_frames = int(math.floor(duration * avg_fps))
+        if num_frames <= 0:
+            stream.thread_type = "AUTO"
+            num_frames = sum(1 for _ in container.decode(stream))
+    if num_frames <= 0:
+        raise ValueError(f"No decodable video frames in {video_path}")
+    return num_frames, avg_fps or 1.0
+
+
+def _upright(image, rotation: int):
+    """Apply a container display-matrix rotation, in degrees, to ``image``.
+
+    PyAV hands back the stored raster and leaves the display matrix for the
+    caller, unlike the ffmpeg CLI which autorotates. Phone clips routinely
+    carry +/-90, so skipping this feeds the model a sideways frame: arrows and
+    digits stop being readable and the model mirrors the motion it reports.
+    """
+    from PIL import Image
+
+    quarter_turns = {
+        90: Image.Transpose.ROTATE_90,
+        180: Image.Transpose.ROTATE_180,
+        270: Image.Transpose.ROTATE_270,
+    }
+    turn = quarter_turns.get(int(rotation) % 360)
+    return image.transpose(turn) if turn is not None else image
+
+
+def _decode_video_frames_rgb(video_path: Path, frame_idx: list[int]) -> list:
+    """Decode presentation-order ``frame_idx`` into upright RGB ``PIL.Image``s."""
+    import av
+
+    wanted = sorted({int(i) for i in frame_idx})
+    if not wanted:
+        return []
+
+    decoded: dict[int, object] = {}
+    with av.open(str(video_path)) as container:
+        stream = container.streams.video[0]
+        stream.thread_type = "AUTO"
+        cursor = 0
+        for position, frame in enumerate(container.decode(stream)):
+            if wanted[cursor] > position:
+                continue
+            image = _upright(frame.to_image(), getattr(frame, "rotation", 0) or 0)
+            while cursor < len(wanted) and wanted[cursor] <= position:
+                decoded[wanted[cursor]] = image
+                cursor += 1
+            if cursor >= len(wanted):
+                break
+
+    if not decoded:
+        raise ValueError(f"Decoded no frames from {video_path} for indices {wanted[:8]}")
+    last_image = decoded[max(decoded)]
+    return [decoded.get(int(i), last_image) for i in frame_idx]
+
+
+def _resize_max_side(image, max_side: int):
+    width, height = image.size
+    longest = max(width, height)
+    if longest <= max_side or max_side <= 0:
+        return image
+    scale = max_side / float(longest)
+    new_size = (max(1, int(round(width * scale))), max(1, int(round(height * scale))))
+    return image.resize(new_size)
+
+
+def _jpeg_bytes(image, *, quality: int = 95) -> bytes:
+    buf = io.BytesIO()
+    image.convert("RGB").save(buf, format="JPEG", quality=quality)
+    return buf.getvalue()
+
+
+def _to_pcm16_bytes(audio_np) -> bytes:
+    import numpy as np
+
+    arr = np.asarray(audio_np).reshape(-1)
+    if arr.dtype != np.int16:
+        arr = (np.clip(arr, -1.0, 1.0) * 32767.0).astype(np.int16)
+    return arr.tobytes()
+
+
+def _pcm16_wav_duration_s(path: Path) -> float:
+    pcm16 = read_pcm16_wav(path)
+    return len(pcm16) / float(PCM16_SAMPLE_RATE * PCM16_BYTES_PER_SAMPLE)
+
+
+def _extract_video_frames(
+    video_path: Path,
+    work_dir: Path,
+    *,
+    fps: float,
+    max_side: int,
+    duration_s: float,
+    stack_frames: int = 1,
+) -> tuple[list[str], list[str | None]]:
+    """Demux JPEG frames only. Frame count follows ``duration_s``, not soundtrack.
+
+    Returns the base frames (one per model unit) and the parallel stacked track.
+    With ``stack_frames=N`` each unit also samples its ``N-1`` interior
+    sub-frames and tiles them into one composite, which is how official duplex
+    raises the visual refresh rate while keeping one second of audio per unit.
+    A unit whose interior falls past the end of the clip stacks nothing.
+    """
+    num_frames, avg_fps = _probe_video_frames_and_fps(video_path)
+    sample_fps = max(float(fps), 1e-6)
+    unit_s = 1.0 / sample_fps
+    timeline_s = max(float(duration_s), unit_s)
+    num_samples = max(1, int(math.ceil(timeline_s * sample_fps - 1e-9)))
+    offsets = unit_subframe_offsets(stack_frames, unit_s=unit_s)
+
+    def frame_at(seconds: float) -> int:
+        # Official get_video_frame_audio_segments uses truncating int(), not
+        # round(), so 29.97 fps lands on the same presentation index.
+        return min(int(seconds * avg_fps), num_frames - 1)
+
+    base_idx = [frame_at(unit * unit_s) for unit in range(num_samples)]
+    sub_times = [
+        [unit * unit_s + offset for offset in offsets if unit * unit_s + offset < timeline_s]
+        for unit in range(num_samples)
+    ]
+    sub_idx = [frame_at(seconds) for times in sub_times for seconds in times]
+    images = _decode_video_frames_rgb(video_path, base_idx + sub_idx)
+    sub_images = iter(images[len(base_idx) :])
+
+    frame_dir = work_dir / "frames"
+    frame_dir.mkdir(parents=True, exist_ok=True)
+    for stale in frame_dir.glob("*.jpg"):
+        stale.unlink()
+    frames_b64: list[str] = []
+    stacked_b64: list[str | None] = []
+    for index, (image, times) in enumerate(zip(images[: len(base_idx)], sub_times), start=1):
+        jpeg = _jpeg_bytes(_resize_max_side(image, max_side))
+        (frame_dir / f"frame_{index:05d}.jpg").write_bytes(jpeg)
+        frames_b64.append(base64.b64encode(jpeg).decode("ascii"))
+        interior = [_resize_max_side(next(sub_images), max_side) for _ in times]
+        if not interior:
+            stacked_b64.append(None)
+            continue
+        composite = concat_frames_b64(interior)
+        (frame_dir / f"stack_{index:05d}.jpg").write_bytes(base64.b64decode(composite))
+        stacked_b64.append(composite)
+    return frames_b64, stacked_b64
+
+
+def _extract_video_soundtrack(video_path: Path, work_dir: Path) -> Path:
+    """Write a 16 kHz mono WAV from the video soundtrack."""
+    try:
+        from vllm.multimodal.media.audio import load_audio
+    except ImportError as exc:  # pragma: no cover
+        raise SystemExit("--input-video needs vLLM audio helpers (load_audio)") from exc
+
+    audio_np, sr = load_audio(str(video_path), sr=PCM16_SAMPLE_RATE, mono=True)
+    work_dir.mkdir(parents=True, exist_ok=True)
+    audio_path = work_dir / "input_16k.wav"
+    write_pcm16_wav(audio_path, _to_pcm16_bytes(audio_np), sample_rate_hz=int(sr))
+    return audio_path
+
+
+def _extract_video_input(
+    video_path: Path,
+    work_dir: Path,
+    *,
+    fps: float,
+    max_side: int,
+    stack_frames: int,
+) -> tuple[Path, list[str], list[str | None]]:
+    """Demux a video into duplex inputs: 16 kHz mono WAV plus JPEG frames.
+
+    Use this only when the video soundtrack is the audio source. When the
+    caller already has ``--input-wav``, extract frames against that WAV
+    duration instead so a silent clip cannot fail ``load_audio``.
+    """
+    audio_path = _extract_video_soundtrack(video_path, work_dir)
+    frames_b64, stacked_b64 = _extract_video_frames(
+        video_path,
+        work_dir,
+        fps=fps,
+        max_side=max_side,
+        duration_s=_pcm16_wav_duration_s(audio_path),
+        stack_frames=stack_frames,
+    )
+    return audio_path, frames_b64, stacked_b64
+
+
+def _resolve_duplex_av_inputs(
+    *,
+    input_wav: str | None,
+    input_video: str | None,
+    work_dir: Path,
+    fps: float,
+    max_side: int,
+    stack_frames: int = 1,
+) -> tuple[str, list[str], list[str | None]]:
+    """Return ``(wav_path, frames_b64, stacked_b64)``. External WAV wins over video audio."""
+    if input_video:
+        video_path = Path(input_video)
+        if input_wav:
+            frames, stacked = _extract_video_frames(
+                video_path,
+                work_dir,
+                fps=fps,
+                max_side=max_side,
+                duration_s=_pcm16_wav_duration_s(Path(input_wav)),
+                stack_frames=stack_frames,
+            )
+            return input_wav, frames, stacked
+        extracted_wav, frames, stacked = _extract_video_input(
+            video_path,
+            work_dir,
+            fps=fps,
+            max_side=max_side,
+            stack_frames=stack_frames,
+        )
+        return str(extracted_wav), frames, stacked
+    if not input_wav:
+        raise SystemExit("provide --input-wav, --input-video, or both")
+    return input_wav, [], []
+
+
+async def run_demo(args: argparse.Namespace) -> dict[str, object]:
     output_dir = Path(args.output_dir)
     stream_writer = _StreamingOutputWriter(output_dir)
 
+    input_wav, video_frames, stacked_video_frames = _resolve_duplex_av_inputs(
+        input_wav=args.input_wav,
+        input_video=args.input_video,
+        work_dir=output_dir / "video_input",
+        fps=args.video_fps,
+        max_side=args.frame_max_side,
+        stack_frames=args.stack_frames,
+    )
+
+    input_pcm16 = read_pcm16_wav(Path(input_wav))
+    if not input_pcm16:
+        raise ValueError("input WAV has no audio")
+
     url = build_realtime_url(
         args.url,
         args.model,
@@ -184,10 +434,12 @@ async def run_demo(args: argparse.Namespace) -> dict[str, object]:
             timeout_s=args.timeout_s,
         )
         stream_event_cursor = len(client.events.events)
-        await client.stream_pcm16(
+        frames_sent = await client.stream_pcm16(
             input_pcm16,
             chunk_ms=args.chunk_ms,
             realtime=not args.no_realtime_pacing,
+            video_frames=video_frames,
+            stacked_video_frames=stacked_video_frames,
         )
         commit_event_cursor = len(client.events.events)
         stream_decision = _latest_model_decision(client.events.events, stream_event_cursor)
@@ -310,6 +562,10 @@ async def run_demo(args: argparse.Namespace) -> dict[str, object]:
                     committed_index,
                 ),
             },
+            "input_video": args.input_video,
+            "video_frames_extracted": len(video_frames),
+            "video_frames_sent": frames_sent,
+            "video_stacked_frames_extracted": sum(frame is not None for frame in stacked_video_frames),
             "audio_bytes": len(audio),
             "audio_chunk_count": len(stream_writer.audio_chunk_paths),
             "audio_chunk_files": [str(path) for path in stream_writer.audio_chunk_paths],
@@ -356,7 +612,48 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--url", default="ws://localhost:8099/v1/realtime?duplex=1")
     parser.add_argument("--model", default="openbmb/MiniCPM-o-4_5")
     parser.add_argument("--session-id")
-    parser.add_argument("--input-wav", required=True)
+    parser.add_argument(
+        "--input-wav",
+        help="Mono 16 kHz PCM16 clip to stream. Optional when --input-video carries the audio track.",
+    )
+    parser.add_argument(
+        "--input-video",
+        help=(
+            "Video to stream as omni duplex input. PyAV demuxes frames and "
+            "vLLM load_audio extracts a 16 kHz mono WAV (unless --input-wav overrides the audio)."
+        ),
+    )
+    parser.add_argument(
+        "--video-fps",
+        type=float,
+        default=1.0,
+        help="Frame extraction rate. The wire contract carries ~1 frame per second of audio.",
+    )
+    parser.add_argument(
+        "--frame-max-side",
+        type=int,
+        default=0,
+        help=(
+            "Optional client-side downscale of the longest side, in pixels. "
+            "0 (default) keeps the capture resolution so the server "
+            "process_image can normalize at scale_resolution=448 from a "
+            "higher-quality source. The web demo never resizes on the client."
+        ),
+    )
+    parser.add_argument(
+        "--stack-frames",
+        type=int,
+        default=1,
+        help=(
+            "Frames sampled per 1 s audio unit. 1 (default) sends the unit's "
+            "frame alone. N > 1 also samples the N-1 sub-frames inside the unit "
+            "and tiles them into one composite sent next to the base frame, so "
+            "motion (arrows, doors, digits changing) is visible at N fps while "
+            "the audio stays 1 s per unit. Official uses 5 for high refresh "
+            "rate mode; the wire carries 2 images per unit at any N because the "
+            "sub-frames share one composite."
+        ),
+    )
     parser.add_argument(
         "--ref-audio",
         required=True,