Back to Details

short-prompt-guide

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Short Prompt Guide

短提示词指南

Efficient prompting for filler shots and atmospheric scenes.
用于创作过渡镜头和氛围感场景的高效提示词方法。

Core Principle: Format + Style Upfront

核心原则：格式与风格前置

The Golden Rule: Always declare format and style FIRST, then describe scene.
Why it works: Establishes aesthetic framework before details. AI interprets description within style context.
Template:
Format & style: [genre/aesthetic]
[Scene description in 1-3 sentences]
Example:
Format & style: Cinematic B-roll, warm color grade
Coffee cup steaming on wooden table at dawn café. 
Slow dolly in, close-up. Warm morning light, soft diffusion. 
Gentle café ambience. (no subtitles)
黄金法则： 始终先声明格式和风格，再描述场景。
为何有效： 在添加细节前先建立美学框架，AI会在风格语境下解读描述内容。
模板：
Format & style: [genre/aesthetic]
[Scene description in 1-3 sentences]
示例：
Format & style: Cinematic B-roll, warm color grade
Coffee cup steaming on wooden table at dawn café. 
Slow dolly in, close-up. Warm morning light, soft diffusion. 
Gentle café ambience. (no subtitles)

When to Use Short Prompts

何时使用短提示词

✅ Ideal For:

✅ 适用场景：

  • Filler/atmosphere shots
  • Transition moments
  • Quick establishing shots
  • Vibe openers
  • B-roll footage
  • Simple product shots
  • Single-subject scenes
  • 过渡/氛围感镜头
  • 转场时刻
  • 快速定场镜头
  • 氛围感开场
  • B-roll素材
  • 简单产品镜头
  • 单主体场景

❌ NOT Suitable For:

❌ 不适用场景：

  • Scenes with dialogue
  • Multiple characters with continuity
  • Complex action sequences
  • Structured narratives
  • Multi-beat choreography
  • 包含对话的场景
  • 有连续性要求的多角色场景
  • 复杂动作序列
  • 结构化叙事
  • 多节拍编排

Decision Rule

决策规则

Use short if: Scene needs <3 sentences to describe
Use long if: Scene needs dialogue, multiple beats, or character continuity
For long prompts, see: long-prompt-guide
使用短提示词的情况： 场景描述只需少于3句话
使用长提示词的情况： 场景包含对话、多节拍内容或角色连续性要求
如需长提示词指南，请查看：long-prompt-guide

Two Approaches

两种方法

Approach 1: Descriptive Prompt (Painting a Picture)

方法1：描述式提示词（描绘画面）

What it is: Describe scene, character, or situation. AI creatively interprets details and camera work.
Best for: Atmospheric shots, mood pieces, establishing shots
Structure:
Format & style: [aesthetic]
Subject/Action: [1-2 compact sentences]
Setting & time: [when/where]
Camera/Composition: [shot + angle + 1 movement]
Lighting/Mood: [brief]
Audio: [ambience/short dialogue] (no subtitles if needed)
Example:
Format & style: Cinematic filler, anime watercolor aesthetic
Subject/Action: A rapper writes lyrics in small bedroom studio. 
Posters on walls, microphone on desk, headphones around neck.
Setting: Night, warm desk lamp glow
Camera: Medium shot, slow push in
Lighting: Warm practical lights, cool window moonlight
Audio: Soft lo-fi beats, pen scratching paper
定义： 描述场景、角色或情境，AI会创造性地解读细节和运镜方式。
最佳适用： 氛围感镜头、情绪片段、定场镜头
结构：
Format & style: [aesthetic]
Subject/Action: [1-2 compact sentences]
Setting & time: [when/where]
Camera/Composition: [shot + angle + 1 movement]
Lighting/Mood: [brief]
Audio: [ambience/short dialogue] (no subtitles if needed)
示例：
Format & style: Cinematic filler, anime watercolor aesthetic
Subject/Action: A rapper writes lyrics in small bedroom studio. 
Posters on walls, microphone on desk, headphones around neck.
Setting: Night, warm desk lamp glow
Camera: Medium shot, slow push in
Lighting: Warm practical lights, cool window moonlight
Audio: Soft lo-fi beats, pen scratching paper

Approach 2: Directive Prompt (Giving a Command)

方法2：指令式提示词（下达命令）

What it is: Direct command with specific actions, cuts, or sequence.
Best for: UGC content, social media clips, product demos, quick reactions
Structure:
Format & style: [aesthetic]
Make a [type] video: [subject] [action sequence]
[Specific cuts/beats]: [timing]
[Audio]: [sounds/dialogue]
Example:
Format & style: UGC reaction video, iPhone 14 Pro Max, vertical 9:16
Make a taste-test reaction: person tries new energy drink
Three fast cuts - open can (crack sound), sip, smile and nod
Audio: Can opening, sip sound, "Wow, that's good!" (no subtitles)
定义： 包含特定动作、剪辑或序列的直接命令。
最佳适用： UGC内容、社交媒体片段、产品演示、快速反应视频
结构：
Format & style: [aesthetic]
Make a [type] video: [subject] [action sequence]
[Specific cuts/beats]: [timing]
[Audio]: [sounds/dialogue]
示例：
Format & style: UGC reaction video, iPhone 14 Pro Max, vertical 9:16
Make a taste-test reaction: person tries new energy drink
Three fast cuts - open can (crack sound), sip, smile and nod
Audio: Can opening, sip sound, "Wow, that's good!" (no subtitles)

Ultra-Minimal Template

极简模板

When you need absolute brevity:
[Format+Style]. [Subject] [Action] in [Setting]. [Camera]. [Lighting]. [Audio]. [Constraints]
Example:
Cinematic B-roll. Coffee cup steaming on wooden table at dawn café. 
Slow dolly in, close-up. Warm morning light, soft diffusion. 
Gentle café ambience. (no subtitles)
Note: Even minimal prompts must include the 8 core components from great-prompt-anatomy, just compressed.
当你需要极致简洁时：
[Format+Style]. [Subject] [Action] in [Setting]. [Camera]. [Lighting]. [Audio]. [Constraints]
示例：
Cinematic B-roll. Coffee cup steaming on wooden table at dawn café. 
Slow dolly in, close-up. Warm morning light, soft diffusion. 
Gentle café ambience. (no subtitles)
注意： 即使是极简提示词也必须包含great-prompt-anatomy中的8个核心组件，只是进行了压缩。

When to Add Detail

何时添加细节

Stay Minimal When:

保持极简的情况：

  • ✅ Simple subject (single object, person)
  • ✅ Standard action (walking, sitting, pouring)
  • ✅ Common setting (café, street, park)
  • ✅ Familiar style (cinematic, documentary)
  • ✅ 简单主体（单个物体、人物）
  • ✅ 标准动作（行走、坐下、倒水）
  • ✅ 常见场景（咖啡馆、街道、公园）
  • ✅ 熟悉风格（电影感、纪录片）

Add Detail When:

需要添加细节的情况：

  • ⚠️ Specific visual needed (exact wardrobe color for continuity)
  • ⚠️ Uncommon action (complex choreography)
  • ⚠️ Unique setting (specific architectural style)
  • ⚠️ Continuity with other shots required
  • ⚠️ 需要特定视觉效果（如为了连续性要求的精确服装颜色）
  • ⚠️ 不常见动作（复杂编排）
  • ⚠️ 独特场景（特定建筑风格）
  • ⚠️ 需要与其他镜头保持连续性

Audio in Short Prompts

短提示词中的音频处理

Keep It Brief:

保持简洁：

  • Ambience: "Soft rainfall, distant traffic"
  • Short dialogue: 
    She says: "Ready?" (no subtitles)
  • Music: "Lo-fi hip hop beats, mellow"
  • Silence: "No background music"
  • 环境音： "Soft rainfall, distant traffic"
  • 简短对话： 
    She says: "Ready?" (no subtitles)
  • 音乐： "Lo-fi hip hop beats, mellow"
  • 静音： "No background music"

Omit Audio When:

可以省略音频的情况：

  • Standard ambience implied (café sounds in café setting)
  • Music not critical to scene mood
  • Silence is default assumption
  • 场景默认包含标准环境音（如咖啡馆场景中的咖啡馆声音）
  • 音乐对场景情绪非必需
  • 默认假设为静音

Common Mistakes to Avoid

需避免的常见错误

❌ Too Vague:

❌ 过于模糊：

"A person doing something interesting"
"A person doing something interesting"

✅ Specific:

✅ 具体明确：

"A chef flambing dessert, blue flame leaping up"
"A chef flambing dessert, blue flame leaping up"

❌ Format Buried:

❌ 格式后置：

"Person walks down street. It's a noir style."
"Person walks down street. It's a noir style."

✅ Format First:

✅ 格式前置：

"Neo-noir style. Person walks down rain-slicked street."
"Neo-noir style. Person walks down rain-slicked street."

❌ Multiple Movements:

❌ 多个运镜动作：

"Dolly in while panning left and tilting up"
"Dolly in while panning left and tilting up"

✅ One Movement:

✅ 单个运镜动作：

"Arc left around subject"
For camera movement vocabulary, see: camera-movements
"Arc left around subject"
如需运镜词汇参考，请查看：camera-movements

❌ Missing Constraints:

❌ 缺少约束条件：

"Person talking"
"Person talking"

✅ With Constraints:

✅ 添加约束条件：

Person says: "Let's go." (no subtitles)
Person says: "Let's go." (no subtitles)

Quick Reference Decision Tree

快速参考决策树

Need dialogue or character continuity?
├─ YES → Use long-prompt-guide
└─ NO → Continue

Simple filler/atmosphere shot?
├─ YES → Use short prompt
└─ NO → Use long-prompt-guide

Describe scene or give command?
├─ DESCRIBE → Descriptive approach
└─ COMMAND → Directive approach

Know exact format/style?
├─ YES → Start with format+style
└─ NO → Browse examples for inspiration
Need dialogue or character continuity?
├─ YES → Use long-prompt-guide
└─ NO → Continue

Simple filler/atmosphere shot?
├─ YES → Use short prompt
└─ NO → Use long-prompt-guide

Describe scene or give command?
├─ DESCRIBE → Descriptive approach
└─ COMMAND → Directive approach

Know exact format/style?
├─ YES → Start with format+style
└─ NO → Browse examples for inspiration

Examples Library

示例库

For 50+ short prompt examples organized by use case, see: references/examples-library.md
Load examples-library.md when:
  • Need inspiration for specific style
  • Learning descriptive vs directive patterns
  • Want to see format variations
  • Exploring different shot types
Stay in SKILL.md when:
  • Understand core principles
  • Just need template reminder
  • Creating familiar shot types
如需按使用场景分类的50+短提示词示例，请查看：references/examples-library.md
何时查看examples-library.md：
  • 需要特定风格的灵感
  • 学习描述式与指令式的模式
  • 想要了解格式变体
  • 探索不同镜头类型
何时使用SKILL.md：
  • 已理解核心原则
  • 只需模板提醒
  • 创作熟悉类型的镜头