[Model][Frontend] MiniMax-H3: Add opt-in planar video response encoding (#6288)

Signed-off-by: MosCloud <bwzhang1991@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/diffusion/utils/media_utils.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import io
+from collections.abc import Iterable
 from fractions import Fraction
 from typing import Any, cast
 
@@ -200,3 +201,70 @@ def mux_video_audio_bytes(
 
     container.close()
     return buf.getvalue()
+
+
+def mux_av_video_audio_bytes(
+    video_frames: Iterable[av.VideoFrame],
+    width: int,
+    height: int,
+    audio_waveform: np.ndarray | None = None,
+    *,
+    fps: float = 25.0,
+    audio_sample_rate: int = 44100,
+    video_codec: str = "h264",
+    audio_codec: str = "aac",
+    crf: str = "18",
+    video_codec_options: dict[str, str] | None = None,
+) -> bytes:
+    """Mux preconstructed video frames and optional audio into MP4 bytes."""
+    buf = io.BytesIO()
+    with cast(Any, av.open(buf, mode="w", format="mp4")) as container:
+        v_stream = cast(
+            av.VideoStream,
+            container.add_stream(video_codec, rate=Fraction(fps).limit_denominator(10000)),
+        )
+        v_stream.width = width
+        v_stream.height = height
+        v_stream.pix_fmt = "yuv420p"
+
+        options: dict[str, object] = {"crf": str(crf)}
+        if video_codec_options:
+            options.update(video_codec_options)
+        v_stream.options = options
+
+        a_stream: av.AudioStream | None = None
+        samples: np.ndarray | None = None
+        layout: str | None = None
+        if audio_waveform is not None:
+            samples = audio_waveform.astype(np.float32)
+            if samples.ndim == 1:
+                samples = samples.reshape(1, -1)
+            elif samples.ndim == 2 and samples.shape[0] > samples.shape[1]:
+                samples = np.ascontiguousarray(samples.T)
+            num_channels = samples.shape[0]
+            layout = "stereo" if num_channels >= 2 else "mono"
+            a_stream = cast(av.AudioStream, container.add_stream(audio_codec, rate=audio_sample_rate))
+            a_stream.layout = layout
+
+        for frame in video_frames:
+            for packet in v_stream.encode(frame):
+                container.mux(packet)
+        for packet in v_stream.encode():
+            container.mux(packet)
+
+        if a_stream is not None and audio_waveform is not None:
+            if samples is None or layout is None:
+                raise ValueError("Audio samples were not prepared for muxing.")
+            audio_frame = av.AudioFrame.from_ndarray(samples, format="fltp", layout=layout)
+            audio_frame.sample_rate = audio_sample_rate
+            # AAC has a one-frame encoder delay. Mark the input waveform as
+            # starting at t=0 so the MP4 muxer writes the corresponding negative
+            # priming timestamp instead of exposing the delay as leading silence.
+            audio_frame.pts = 0
+            audio_frame.time_base = Fraction(1, audio_sample_rate)
+            for packet in a_stream.encode(audio_frame):
+                container.mux(packet)
+            for packet in a_stream.encode():
+                container.mux(packet)
+
+    return buf.getvalue()