h3-prompt-writing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

H3 提示词写作（底座）

H3 Prompt Writing (Base)

本技能集的通用底座：只负责把意图写成 H3 可直接吃的提示词。
风格题材（产品片、3D、纸艺等）见同仓库其他 skill；它们产出草稿后，可用本 skill 压成标准字段。

This is the universal base of the skill set: it only converts intentions into prompts that H3 can directly use.
For styles and themes (product videos, 3D, paper art, etc.), refer to other skills in the same repository; after they generate drafts, you can use this skill to compress them into standard fields.

何时用 / 不用

When to Use / Not to Use

用：写或改 H3 提示词；图/视频/音频参考要标签化；跨镜连续；道具交接等精确物理。
不用： 与 H3 无关的文案、长剧剧本、后期工程说明。

Use: Writing or revising H3 prompts; tagging image/video/audio references; continuous cross-shot sequences; precise physical interactions like prop handovers.
Do Not Use: Copy unrelated to H3, long drama scripts, post-production project instructions.

输出规格

Output Specifications

项	值
时长	4–15s
画幅	21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
分辨率	默认短边 768，可 2K
帧率/音频	24fps；立体声 32kHz

模式	输入	写法要点
T2VA	纯文本	完整视听时间线
I2VA	1 图首帧	从图起锚向前发展
FL2VA	首+尾 2 图	首→尾连续路径；默认单镜插值
L2VA	1 图尾帧	合理前态 → 收敛尾帧
Ref2VA	图≤9 视频≤3 音频≤3 总≤12	六段结构；标签全局同义

Item	Value
Duration	4–15s
Aspect Ratio	21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
Resolution	Default short side 768, optional 2K
Frame Rate/Audio	24fps; Stereo 32kHz

Mode	Input	Key Writing Points
T2VA	Text-only	Complete audio-visual timeline
I2VA	1 first-frame image	Anchor from the image and develop forward
FL2VA	2 images (first + last)	Continuous path from first to last frame; default single-shot interpolation
L2VA	1 last-frame image	Reasonable previous state → converge to the last frame
Ref2VA	≤9 images, ≤3 videos, ≤3 audios, total ≤12	Six-section structure; globally synonymous tags

写法流程

Writing Process

判模式。

读

references/base-zh.txt

（基础）或

ref-zh.txt

（全参考）；英文原版

base-en.txt

ref-en.txt

。

描述太粗 →「八步扩展」；用户已给完整分镜 → 只查时长/时间戳/编号/矛盾，不擅自压缩。
强连续 / 多有序图 / 精确物理 → 先写中文分镜规划，再压终稿。
终稿：字段名、镜头标记、关系标记用英文固定写法；正文默认英文（更稳）；对白/歌词/画面字保留原文。用户要中文正文时字段名不变。

Determine the mode.
Read
```
references/base-zh.txt
```
(basic) or
```
ref-zh.txt
```
(full reference); English versions are
```
base-en.txt
```
/
```
ref-en.txt
```
.
If the description is too vague → use the "Eight-Step Expansion"; if the user has provided complete storyboards, only check duration/timestamps/numbering/contradictions, do not compress without permission.
For strong continuity / multiple ordered images / precise physics → first write a Chinese storyboard plan, then compress into the final draft.
Final Draft: Field names, shot markers, and relationship markers use fixed English expressions; the main text is in English by default (more stable); keep the original text for dialogue/lyrics/on-screen text. When the user requests Chinese main text, keep field names unchanged.

八步扩展

Eight-Step Expansion

输出目标 → 主体与参考资产 → 时间线 → 场景 → 镜头 → 视觉风格 → 声音 → 约束（必保/禁止）。
不臆造品牌、对白、不安全内容。

Output target → Subject and reference assets → Timeline → Scene → Shot → Visual style → Sound → Constraints (required/prohibited).
Do not invent brands, dialogue, or unsafe content.

基础模式终稿

Final Draft for Basic Modes

模式指令（首行；T2VA 无）

Mode Instruction (First line; none for T2VA)

I2VA

text

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

FL2VA（

=末镜号，

S.SS

=时长两位小数）

text

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.

L2VA

text

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.

空一行后写三字段：

text

integrated_multimodal_description: [Shot 1] ...

overall_soundscape: ...

non_diegetic_music: ...

字段	写什么
`integrated_multimodal_description`	时间线上的画面、动作、镜头、说话人、对白/唱、画内声
`overall_soundscape`	全片环境/物理/非语言人声；1–4 句；勿重复对白
`non_diegetic_music`	仅观众可听配乐（乐器、速度、动态）；无则 `N/A`

I2VA

text

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

FL2VA (

=last shot number,

S.SS

=duration with two decimal places)

text

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.

L2VA

text

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.

Leave a blank line and write three fields:

text

integrated_multimodal_description: [Shot 1] ...

overall_soundscape: ...

non_diegetic_music: ...

Field	Content to Write
`integrated_multimodal_description`	On-screen visuals, actions, shots, speakers, dialogue/singing, in-screen sounds on the timeline
`overall_soundscape`	Full-video environment/physical/non-verbal human sounds; 1–4 sentences; do not repeat dialogue
`non_diegetic_music`	Only background music audible to the audience (instruments, tempo, dynamics); write `N/A` if none

关键帧进描述

Keyframes in Description

I2VA：
```
<Picture 1>
```
=0.00s 首帧 → 锚点 → 起势 → 发展 → 结果
FL2VA：首态 → 可观测中间变化 → 收窄 → 尾态；尾落在末镜片尾
L2VA：前态 → 路径 → 末镜对齐图

I2VA:
```
<Picture 1>
```
= 0.00s first frame → anchor → momentum → development → result
FL2VA: Initial state → observable intermediate changes → narrowing → final state; end at the last shot's end frame
L2VA: Previous state → path → align with the last shot's frame

镜头与运镜

Shots and Camera Movements

```
[Shot 1]
```
无时间戳；后镜
```
[Shot N] At 00:MM.SSS, ...
```
，切点递增且 ≤ 片长
普切：
```
the camera cuts to
```
等；叠化仅用户明确要求
运镜写进句内：类型 + 需要时的幅度/速度（Zoom/Push/Pan/Truck/Tilt/Pedestal/Arc/Tracking/Static/Shake/POV/Roll；
```
with small|large amplitude
```
；
```
at slow|fast speed
```
）

```
[Shot 1]
```
has no timestamp; subsequent shots use
```
[Shot N] At 00:MM.SSS, ...
```
, with increasing cut points ≤ video length
Standard cuts:
```
the camera cuts to
```
etc.; cross-dissolve only if explicitly requested by the user
Write camera movements within the sentence: type + amplitude/speed if needed (Zoom/Push/Pan/Truck/Tilt/Pedestal/Arc/Tracking/Static/Shake/POV/Roll;
```
with small|large amplitude
```
;
```
at slow|fast speed
```
)

说话人与字

Speakers and Text

```
(S1)
```
```
(S2)
```
跨镜稳定；合唱
```
(S1,S2)
```
对白只在
```
<d>[Language] ...</d>
```
，原文不改写
画外音：
```
says in an off-screen voiceover
```
+ 在画闭嘴
跨切
```
<scenetrans>
```
；片尾截断
```
<cutoff>
```
画面字：英文双引号包原文

```
(S1)
```
```
(S2)
```
remain stable across shots; chorus uses
```
(S1,S2)
```
Dialogue is only placed within
```
<d>[Language] ...</d>
```
, do not rewrite the original text
Voiceover:
```
says in an off-screen voiceover
```
+ ensure the character's mouth is closed on-screen
Cross-cut:
```
<scenetrans>
```
; end truncation:
```
<cutoff>
```
On-screen text: Wrap original text in English double quotes

模式骨架

Mode Frameworks

模式	骨架
T2VA	风格+构图 → 动作与声 → 切镜补信息
I2VA	首帧全锁 → 起势 → 发展 → 结果
FL2VA	首态 → 中间变化 → 尾态
L2VA	前态 → 路径 → 落尾帧

松散单段：一段紧凑即可。多有序图/强物理：用下方分镜规划。

Mode	Framework
T2VA	Style + composition → actions and sounds → cut shots to supplement information
I2VA	Lock first frame completely → momentum → development → result
FL2VA	Initial state → intermediate changes → final state
L2VA	Previous state → path → end at last frame

Loose single segment: A compact single segment is sufficient. For multiple ordered images/strong physics: use the storyboard plan below.

全参考 Ref2VA

Full Reference Ref2VA

顺序固定：

text

subject_definitions:
summary:
retention_analysis:
detailed_description:
overall_soundscape:
non_diegetic_music:

标签	用途
`<Subject N>`	可复用可见内容（非源文件本身）
`<Picture N>`	图作具体帧/构图锚时单独建；仅定义角色则写进 Subject
`<Video N>`	剪辑源、续写起点、整片结构
`<Audio N>`	拷贝或参考的音频

summary

前缀：

keyframe completion

reference generation

video editing

video continuation

audio reuse

audio reference

，多类型用

。

画面保留标记：

fully_preserved

partially_preserved

attribute_transfer

weak_reference

音频：

fully_copy

partially_copy

reference

weak_reference

detailed_description

：风格 1–2 句 → 逐镜；生成任务约 350–500 英文词；标签首次出现写清，后镜只复用。
细则与完整例见

references/ref-zh.txt

。

Fixed order:

text

subject_definitions:
summary:
retention_analysis:
detailed_description:
overall_soundscape:
non_diegetic_music:

Tag	Usage
`<Subject N>`	Reusable visible content (not the source file itself)
`<Picture N>`	Create separately when using images as specific frames/composition anchors; only write into Subject if defining roles
`<Video N>`	Editing source, continuation starting point, full-video structure
`<Audio N>`	Audio to copy or reference

summary

prefixes:

keyframe completion

reference generation

video editing

video continuation

audio reuse

audio reference

, use

for multiple types.

Visual retention markers:

fully_preserved

partially_preserved

attribute_transfer

weak_reference

Audio:

fully_copy

partially_copy

reference

weak_reference

detailed_description

: 1–2 sentences about style → shot-by-shot description; approximately 350–500 English words for generation tasks; clarify tags when first mentioned, reuse them in subsequent shots.
For detailed rules and complete examples, see

references/ref-zh.txt

中文分镜规划（再压终稿）

Chinese Storyboard Plan (Then Compress into Final Draft)

适用：≥2 有序图、跨镜连续、精确交接。

4–15s 内物理可行；每镜一个主动作节拍
时间戳连续，末点 =
```
D
```
；默认 0.5s 精度
两级时间轴：镜级范围 + 镜内微节拍（建立/预备/核心/稳定）
镜 N 结束状态锁定 = 镜 N+1 起始（姿、视、双手、道具主/位/连接、机位侧）
交接因果：归属 → 接触拿稳 → 松手 → 新归属；勿压成一句糊话

Applicable for: ≥2 ordered images, continuous cross-shot sequences, precise handovers.

Physically feasible within 4–15s; one main action beat per shot
Timestamps are continuous, end point =
```
D
```
; default precision is 0.5s
Two-level Timeline: Shot-level range + micro-beats within the shot (setup/preparation/core/stabilization)
End state of Shot N = starting state of Shot N+1 (posture, gaze, hands, prop owner/location/connection, camera side)
Handover causality: Ownership → hold firmly upon contact → release → new ownership; do not compress into ambiguous sentences

模板

Template

text

【输出规格】{duration}s · {ratio} · {用途} · {N}张有序分镜图 · 不跳镜 · 锁人物服装位置道具

【整体风格】{媒介} · {视觉} · {光色纹理节奏运镜} · 场景{…} · 声音{…}

【人物与空间】人物1/2：外观与固定位置 · 硬约束{脸发型服装座位朝向…}

【道具】全片仅{名称数量} · 初态{主/手/位/连接} · 禁凭空增减跳位暗改归属

【两级时间轴】
镜头1｜0:00-{T1}｜{D1}s｜图1
运镜：…  起始：…  微轴：建立→预备→核心→保持  结束锁定：…
镜头2｜… 起始=镜头1结束锁定 …

【动作顺序】A→B→C  每镜一事  交接写清谁不动/谁拿稳/谁松手
【负面】禁身份漂移变装换位闪烁畸形多余肢物体跳变跳切字幕水印

交接微时序（耳机）见写作时按 0.5s 级拆「取出 → 停在两人之间 → 对方夹稳后才松手 → 未塞耳」。

规划后：基础模式写入

integrated_multimodal_description

；全参考写入

subject_definitions

detailed_description

retention_analysis

。

text

【Output Specifications】{duration}s · {ratio} · {purpose} · {N} ordered storyboard images · No shot skipping · Lock character clothing, positions, and props

【Overall Style】{medium} · {visuals} · {lighting, color, texture, rhythm, camera movement} · Scene{…} · Sound{…}

【Characters and Space】Character 1/2: Appearance and fixed position · Hard constraints{face, hairstyle, clothing, seat, orientation…}

【Props】Only {name, quantity} in the whole video · Initial state{owner/hand/location/connection} · 禁凭空增减跳位暗改归属

【Two-level Timeline】
Shot 1｜0:00-{T1}｜{D1}s｜Image 1
Camera Movement:…  Start:…  Micro-axis: Setup→Preparation→Core→Hold  End Lock:…
Shot 2｜… Start = Shot 1 End Lock …

【Action Sequence】A→B→C  One action per shot  Clearly write who stays still/who holds firmly/who releases during handover
【Negative Constraints】Forbid identity drift, costume changes, position shifts, flickering, deformities, extra limbs, object jumps, jump cuts, subtitles, watermarks

For micro-timing of handovers (e.g., headphones), split into 0.5s steps during writing: "Take out → stop between two people → release only after the other party holds firmly → not inserted into ear".

After planning: For basic modes, write into

integrated_multimodal_description

; for full references, write into

subject_definitions

detailed_description

retention_analysis

终稿自检

Final Draft Self-Check

模式与指令行正确
字段顺序/标签格式对
时间连续，末点=时长
无悬空标签；镜间状态可对账
对白/可见字原文；未擅自加品牌对白
声景与配乐字段分工正确

参考	内容
`base-zh.txt` / `ref-zh.txt`	中文指南 + 英文范例
`base-en.txt` / `ref-en.txt`	官方英文原版

Correct mode and instruction line
Correct field order/tag format
Continuous timeline, end point = duration
No dangling tags; inter-shot states are reconcilable
Original dialogue/visible text preserved; no unauthorized brands or dialogue added
Correct division of labor between soundscape and music fields

Reference	Content
`base-zh.txt` / `ref-zh.txt`	Chinese guide + English examples
`base-en.txt` / `ref-en.txt`	Official English original