视频理解

{
    "id": "fbfdb524-f4c8-41e6-b0a3-31520f6198c7_0b8b3ccec31e40868b76109308ed9329",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "The video features a small, white kitten sitting on a polished wooden floor indoors. The scene is brightly lit by natural sunlight streaming in from a window on the left, which is partially covered by a beige curtain. The light casts distinct shadows on the floorboards. To the right, a large green potted plant (resembling a Monstera) is visible in the background. The kitten, which has striking blue eyes, sits facing forward but glances slightly to the side. It briefly opens its mouth, as if meowing or yawning. The overall atmosphere is warm, calm, and sunny.",
                "role": "assistant",
                "tool_calls": null,
                "reasoning_content": "The user wants a description of the video content.\n\n1.  **Analyze the video:**\n    *   **Subject:** A small, white kitten.\n    *   **Setting:** Indoors, near a window. There's a wooden floor. A curtain hangs to the left. A potted plant (Monstera) is visible in the background to the right.\n    *   **Lighting:** Bright natural sunlight is streaming in from the left (likely a window), casting strong shadows and highlights on the floor and the kitten.\n    *   **Action:** The kitten is sitting on the floor. It's looking slightly to its left (viewer's right). It opens its mouth briefly, possibly meowing or yawning, but there's no audio. Then it looks forward again. It's a very short clip, essentially a still shot with minor movement.\n    *   **Details:** Blue eyes, white fur, pink nose. The curtain is beige/white striped. The floor is polished wood.\n\n2.  **Draft the description:**\n    *   Start with the main subject: A small white kitten.\n    *   Describe the location: Sitting on a wooden floor near a window.\n    *   Describe the lighting: Sunlight is streaming in, creating a warm atmosphere.\n    *   Describe the background elements: A curtain on the left, a green plant on the right.\n    *   Describe the kitten's features: White fur, blue eyes.\n    *   Describe the action: The kitten looks around and opens its mouth slightly.\n\n3.  **Refine the description:**\n    *   \"The video features a small white kitten with blue eyes sitting on a polished wooden floor.\"\n    *   \"The setting appears to be a cozy room with bright sunlight streaming in through a window on the left.\"\n    *   \"A beige curtain hangs beside the window.\"\n    *   \"To the right, a green potted plant is visible in the background.\"\n    *   \"The kitten is facing forward but looks slightly to the side, opening its mouth briefly as if meowing or yawning.\"\n    *   \"The lighting creates distinct shadows on the floor.\"\n\n4.  **Final Polish:** Combine into a coherent paragraph. Ensure it covers the visual aspects clearly.\n\n    *   *Draft:* The video shows a white kitten with bright blue eyes sitting on a shiny wooden floor. Sunlight is pouring in from a window on the left, illuminating the kitten and the floor. There is a curtain to the left and a large leafy plant in the background on the right. The kitten opens its mouth slightly and looks around. The scene is calm and well-lit.\n\n    *   *More detailed:* The video captures a serene moment featuring a small, white kitten sitting on a polished wooden floor bathed in natural sunlight. The light streams in from a window on the left, partially covered by a beige curtain, casting long shadows across the floor. To the right, the large green leaves of a monstera plant add a touch of nature to the indoor setting. The kitten, with its striking blue eyes, faces the camera but glances to the side, briefly opening its mouth as if letting out a soft meow or a yawn. The overall atmosphere is warm and peaceful.\n\n5.  **Output generation:** Present the description clearly to the user."
            }
        }
    ],
    "created": 1790008279,
    "model": "mimo-v2.6-pro",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 807,
        "prompt_tokens": 1260,
        "total_tokens": 2067,
        "completion_tokens_details": {
            "reasoning_tokens": 684
        },
        "prompt_tokens_details": {
            "audio_tokens": 19,
            "cached_tokens": 1216,
            "video_tokens": 1144
        }
    }
}

"""
根据视频的时长、分辨率，估算 API 调用所消耗的 Token 数。
用户可通过 fps 和 media_resolution 两个参数控制精细度：
  - fps: 每秒抽帧数，默认 2，范围 [0.1, 10]。越高时序越精细，Token 越多。
  - media_resolution: 单帧分辨率档次。"default" 平衡效果与效率；"max" 提升细节识别。
"""

import math

def estimate_video_tokens(
    duration: float,
    width: int,
    height: int,
    fps: float = 2.0,
    media_resolution: str = "default",
    mute: bool = False,
) -> int:
    """
    估算视频输入的 Token 数。

    Args:
        duration:         视频时长（秒）
        width:            视频宽度（像素）
        height:           视频高度（像素）
        fps:              抽帧帧率，默认 2，范围 [0.1, 10]
        media_resolution: "default" 或 "max"
        mute:             True 则不计算音频 Token

    Returns:
        预估总 Token 数
    """
    # ---- 常量 ----
    PATCH, MERGE, T_PATCH = 16, 2, 2
    SPATIAL = PATCH * MERGE                         # 32
    PIX_PER_TOKEN = SPATIAL ** 2                    # 1024
    MAX_TOTAL_TOKENS = 131072
    TOTAL_MAX_PIX = MAX_TOTAL_TOKENS * PIX_PER_TOKEN
    MIN_PIX, MAX_PIX = 8192, 8388608
    MAX_FRAMES = 2048
    DEFAULT_MAX_FRAME_TOKEN = 300

    # ---- 1. 抽帧数 ----
    nframes = math.ceil(duration * fps)
    nframes = min(nframes, MAX_FRAMES)
    nframes = max(math.ceil(nframes / T_PATCH) * T_PATCH, T_PATCH)

    # ---- 2. 单帧像素预算 ----
    max_pix = TOTAL_MAX_PIX * T_PATCH // nframes
    if media_resolution != "max":
        max_pix = min(max_pix, DEFAULT_MAX_FRAME_TOKEN * PIX_PER_TOKEN)
    max_pix = max(MIN_PIX, min(max_pix, MAX_PIX))

    # ---- 3. 缩放分辨率 ----
    h, w = height, width
    if min(h, w) < SPATIAL:
        if h < w:
            w = int(w * SPATIAL / h); h = SPATIAL
        else:
            h = int(h * SPATIAL / w); w = SPATIAL
    h_bar = round(h / SPATIAL) * SPATIAL
    w_bar = round(w / SPATIAL) * SPATIAL
    if h_bar * w_bar > max_pix:
        beta = math.sqrt(h * w / max_pix)
        h_bar = math.floor(h / beta / SPATIAL) * SPATIAL
        w_bar = math.floor(w / beta / SPATIAL) * SPATIAL
    elif h_bar * w_bar < MIN_PIX:
        beta = math.sqrt(MIN_PIX / (h * w))
        h_bar = math.ceil(h * beta / SPATIAL) * SPATIAL
        w_bar = math.ceil(w * beta / SPATIAL) * SPATIAL

    # ---- 4. Token 计算 ----
    grids = nframes // T_PATCH                       # 时序网格数
    tokens_per_grid = (h_bar // PATCH) * (w_bar // PATCH) // (MERGE ** 2)
    vision = grids * tokens_per_grid
    timestamps = grids * (5 if fps > 2 else 3)       # 时间戳文本 token
    special = grids * 2 + 2                           # 特殊标记

    # ---- 5. 音频 Token ----
    audio = 0
    if not mute:
        spec_len = int(duration * 24000) // 240 + 1
        t = (spec_len - 1) // 2 + 1
        t = t // 2 + int(t % 2 != 0)
        audio = math.ceil(t / 4) + 2                 # +2 for audio special tokens

    return vision + timestamps + special + audio

# ============ 示例 ============
if __name__ == "__main__":
    # 一个 1080p、60 秒的视频
    tokens = estimate_video_tokens(duration=60, width=1920, height=1080)
    print(f"默认参数 (fps=2, default): {tokens:,} tokens")

    tokens = estimate_video_tokens(duration=60, width=1920, height=1080, fps=5)
    print(f"高帧率  (fps=5, default): {tokens:,} tokens")

    tokens = estimate_video_tokens(duration=60, width=1920, height=1080, media_resolution="max")
    print(f"高分辨率 (fps=2, max):     {tokens:,} tokens")

    tokens = estimate_video_tokens(duration=60, width=1920, height=1080, mute=True)
    print(f"静音    (fps=2, mute):    {tokens:,} tokens")

总 Tokens 数 ≈ 音频时长（单位：秒）* 6.25