MiniMax H3 提示词撰写指南：五种模式的官方结构

integrated_multimodal_description: [Shot 1] ...

overall_soundscape: ...

non_diegetic_music: ...

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot N) aligns with the S.SS-second mark of the target video.

How the reference pictures align with the target video — <Picture 1> (from [Shot N]) aligns with the S.SS-second mark of the target video.

[Shot 2] At 00:03.500, the camera cuts to...

The camera pushes in with small amplitude at slow speed toward the folded letter in her hands.
The camera pans right with large amplitude at fast speed, revealing the open doorway.
The camera holds a static shot as the runner exits the frame.

The young woman with a quiet, breathy voice (S1) says: <d>[English] I get off at the next station.</d>

The man (S1) says in an off-screen voiceover: <d>[English] I still remember that road.</d> while his lips remain completely closed.

A red neon sign reading "营业中" glows above the doorway.

## 全引用模式（Ref2VA）：六段式格式

Ref2VA 重写采用按此固定顺序排列的六个部分：

| 部分 | 用途 |
|---------|---------|
| `subject_definitions` | 定义被引用的内容及其标签 |
| `summary` | 任务类型 + 目标视频 + 主要引用关系 |
| `retention_analysis` | 每个被引用项如何被保留/迁移 |
| `detailed_description` | 按播放顺序的逐镜头描述 |
| `overall_soundscape` | 环境音与物理音效 |
| `non_diegetic_music` | 仅面向观众的背景音乐 |

### 引用标签

| 标签 | 含义 |
|-------|---------|
| `<Subject N>` | 从引用内容中抽象出的可复用可见内容 |
| `<Picture N>` | 作为画面锚点或规划参考的引用图像 |
| `<Video N>` | 作为剪辑来源/续写/结构的引用视频 |
| `<Audio N>` | 被复制或引用的音频信号 |

标签在全部六个部分中保持其含义。`<Video N>` 与 `<Audio N>` 独立编号。

### `summary` 中的任务类型

| 任务类型 | 使用时机 |
|-----------|----------|
| `keyframe completion` | 图像作为具体的画面锚点 |
| `reference generation` | 素材提供引导，但并非具体画面 |
| `video editing` | 直接修改来源视频 |
| `video continuation` | 新内容从来源视频继续 |
| `audio reuse` | 复用同一音频信号 |
| `audio reference` | 仅引用音频的风格/音色/内容 |

用 ` + ` 组合多种类型，例如 `[video continuation + keyframe completion]`。

### `retention_analysis` 中的关系标记

**可见内容：** `fully_preserved`、`partially_preserved`、`attribute_transfer`、`weak_reference`
**音频：** `fully_copy`、`partially_copy`、`reference`、`weak_reference`

<Subject 1> (appears in [Shot 1], [Shot 3]): fully_preserved - ...
<Audio 1>: reference - the target speaker follows <Audio 1>'s voice timbre without copying the original signal.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium-wide shot frames a baker opening the shutters of a small street bakery before sunrise. The camera pushes in with small amplitude at slow speed as the middle-aged baker with a calm, slightly raspy voice (S1) places a fresh loaf on the wooden counter and says: <d>[English] First batch of the morning.</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of steam rising from the sliced bread while the baker's final words carry over from the previous shot.

overall_soundscape: Wooden shutters scrape open over a quiet street as trays clink softly inside the bakery. The doorbell rings once, followed by light footsteps and the crisp sound of bread being sliced.

non_diegetic_music: A soft acoustic-guitar pattern at a moderate tempo, joined by sparse upright-bass notes and a gentle fade at the end.