storyboard-breaker

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

分镜拆解指南

Storyboard Decomposition Guide

拆解原则

Decomposition Principles

每个镜头聚焦单一动作，描述要详尽具体。每个镜头时长 10-15 秒。

Each shot focuses on a single action, with detailed and specific descriptions. Each shot lasts 10-15 seconds.

镜头要素

Shot Elements

镜头标题：3-5字概括核心内容（如"噩梦惊醒"）
时间：具体时分 + 光线描述
地点：场景完整描述 + 空间布局 + 环境细节
景别：远景/全景/中景/近景/特写
角度：平视/仰视/俯视/侧面/背面
运镜：固定/推镜/拉镜/摇镜/跟镜/移镜
动作：谁 + 具体怎么做 + 肢体细节 + 表情
对话：该镜头的完整对话
画面结果：动作的即时后果 + 视觉细节
氛围：光线 + 色调 + 声音 + 整体氛围
时长：每个镜头 10-15 秒
静态画面提示词：
```
image_prompt
```
，用于首帧/尾帧/镜头图片生成
视频提示词：
```
video_prompt
```
，按 3 秒分段的视频生成描述（必填）
配乐提示词：
```
bgm_prompt
```
，描述该镜头适合的配乐风格
音效提示词：
```
sound_effect
```
，描述该镜头关键环境音/动作音
场景关联：若能匹配已有场景，必须填写
```
scene_id
```
角色关联：填写
```
character_ids
```
，绑定当前镜头涉及的 0 到多个角色

Shot Title: Summarize the core content in 3-5 characters (e.g. "Waking up from a nightmare")
Time: Specific time + light description
Location: Complete scene description + spatial layout + environmental details
Shot Size: Long shot/full shot/medium shot/close shot/close-up
Angle: Eye level/low angle/high angle/side view/back view
Camera Movement: Fixed/push in/pull out/pan/track/dolly
Action: Who + specific operation + body details + expression
Dialogue: Complete dialogue for this shot
Frame Result: Immediate consequence of the action + visual details
Atmosphere: Light + color tone + sound + overall atmosphere
Duration: 10-15 seconds per shot
Static Frame Prompt:
```
image_prompt
```
, used for generating first frame/last frame/shot images
Video Prompt:
```
video_prompt
```
, video generation description segmented by 3 seconds (required)
Background Music Prompt:
```
bgm_prompt
```
, describes the suitable soundtrack style for this shot
Sound Effect Prompt:
```
sound_effect
```
, describes the key ambient sound/action sound of this shot
Scene Association: If it matches an existing scene,
```
scene_id
```
must be filled in
Character Association: Fill in
```
character_ids
```
to bind 0 or multiple characters involved in the current shot

视频提示词格式

Video Prompt Format

每个镜头必须包含

video_prompt

字段，用于驱动 AI 视频生成：

0-3秒：<location>咖啡厅</location>，近景，<role>小明</role>低头看手机，表情焦虑。
<n>3-6秒：<location>咖啡厅</location>，全景，门铃响，<role>小红</role>推门走入。
<n>6-9秒：<location>咖啡厅</location>，中景，<role>小红</role>微笑走向小明，坐下。

标签说明：

```
<location>地点</location>
```
— 场景标记
```
<role>角色名</role>
```
— 角色标记
```
<voice>角色名</voice>
```
— 画外音/旁白标记
```
<n>
```
— 时间段分隔符

Each shot must contain the

video_prompt

field to drive AI video generation:

0-3秒：<location>咖啡厅</location>，近景，<role>小明</role>低头看手机，表情焦虑。
<n>3-6秒：<location>咖啡厅</location>，全景，门铃响，<role>小红</role>推门走入。
<n>6-9秒：<location>咖啡厅</location>，中景，<role>小红</role>微笑走向小明，坐下。

Label Description:

```
<location>location</location>
```
— Scene marker
```
<role>character name</role>
```
— Character marker
```
<voice>character name</voice>
```
— Voiceover/narration marker
```
<n>
```
— Time segment separator

使用步骤

Usage Steps

调用
```
read_storyboard_context
```
读取剧本、角色、场景、已有分镜摘要
先基于剧本完成镜头拆解，确保总时长和叙事连续性合理

为每个镜头补全完整字段：

title / shot_type / angle / movement / location / time / character_ids / action / dialogue / description / result / atmosphere / image_prompt / video_prompt / bgm_prompt / sound_effect / duration / scene_id

调用
```
save_storyboards
```
一次性保存完整分镜
如需调整，调用
```
update_storyboard
```
修改具体镜头

Call
```
read_storyboard_context
```
to read scripts, characters, scenes, and existing storyboard summaries
Complete shot decomposition based on the script first to ensure reasonable total duration and narrative continuity

Fill in complete fields for each shot:

title / shot_type / angle / movement / location / time / character_ids / action / dialogue / description / result / atmosphere / image_prompt / video_prompt / bgm_prompt / sound_effect / duration / scene_id

Call
```
save_storyboards
```
to save the complete storyboards at one time
If adjustment is needed, call
```
update_storyboard
```
to modify specific shots

场景关联规则

Scene Association Rules

优先使用
```
read_storyboard_context
```
返回的
```
scenes
```
```
location + time
```
可明确匹配时，必须回填正确
```
scene_id
```
不要凭空生成不存在的场景 ID
如果剧本内容明显落在已有场景中，不要重复创造新场景描述

Prioritize using
```
scenes
```
returned by
```
read_storyboard_context
```
When
```
location + time
```
can be clearly matched, the correct
```
scene_id
```
must be filled back
Do not generate non-existent scene IDs out of thin air
If the script content clearly falls into an existing scene, do not repeatedly create new scene descriptions

角色绑定规则

Character Binding Rules

```
character_ids
```
必须从
```
read_storyboard_context
```
返回的角色列表中选择
一个镜头可以没有角色，也可以绑定多个角色
只要镜头里有明确出场、被看见、发生动作或说话的角色，都应绑定进去
纯环境镜头、空镜头、物件镜头可以传空数组

```
character_ids
```
must be selected from the character list returned by
```
read_storyboard_context
```
A shot can have no characters, or bind multiple characters
As long as there are characters who clearly appear, are seen, perform actions or speak in the shot, they should be bound
Pure environmental shots, empty shots, and object shots can pass an empty array

质量要求

Quality Requirements

```
description
```
要适合人读，
```
video_prompt
```
要适合模型生成，二者不要互相替代
```
image_prompt
```
要突出单帧构图、角色外观、环境和光线
```
video_prompt
```
要突出时间推进、动作变化、镜头语言
```
bgm_prompt
```
和
```
sound_effect
```
用简洁短语即可，但不能空泛到只有“紧张”“悲伤”
若存在旁白，统一写入
```
dialogue
```
，格式为
```
旁白：内容
```

```
description
```
should be human-readable,
```
video_prompt
```
should be suitable for model generation, and the two should not replace each other
```
image_prompt
```
should highlight single-frame composition, character appearance, environment and light
```
video_prompt
```
should highlight time progression, action changes, and camera language
```
bgm_prompt
```
and
```
sound_effect
```
can use concise phrases, but should not be too vague such as only "tense" or "sad"
If there is narration, write it into
```
dialogue
```
uniformly, in the format of
```
Narration: content
```