| name | vertical-big-word-cover |
| description | 竖版大字报封面制作。第一眼只有一个大钩子，人物置顶，大字压在人物后面，底部一个结果承诺。
适合9:16短视频封面、真实案例、避坑内容、老板视角、方法论内容。
当用户说"做封面"、"短视频封面"、"大字报封面"、"竖版封面"、"封面图"时使用。
|
Vertical Big Word Cover
Goal
Create a 9:16 short-video cover that works as an attention interceptor, not an information page. The viewer should see one hook, one face, one result promise — nothing more.
Required Inputs
- Source video or clearest speaker frame
- Topic or conflict point
- Result promise the viewer should remember
- Optional: category label (e.g. "真实案例", "AI落地指南")
Core Principle
A cover is not an explanation page. It is an attention interceptor.
The shared trait of effective covers is NOT "lots of text" — it is:
- One big hook at first glance
- Speaker face on the top visual layer
- Large text behind the person, poster-style
- One result promise at the bottom
- Small labels only for classification, never for explanation
Layer Order (bottom to top)
- Background: Source video frame, blurred, darkened, desaturated
- Big text layer: 4-6 characters, red or white, thick stroke, OK to be partially covered by person
- Person layer: Cutout or sticker-style speaker, on top, slight stroke or glow
- Result layer: Bottom text, usually cyan-green / yellow / white combination
- Label layer: Category tags — small and clear (e.g. "真实案例", "老板必看")
Person must cover the big text, never the reverse.
Copy Formula
Extract "conflict + action + result", not "asset name":
Conflict: 别做X / 别问X / X不等于Y
Action: 先做Y / 先拆Y / 先跑通Y
Result: 变成Z / N天见效 / 3步搞定Z
Bad example: "一堆资料" — just an asset, no relation to the outcome.
Good example: "别问需求 / 先拆资料 / 一堆文档变AI工作流"
Text Rules
Three layers maximum:
- Category label: 2-6 characters (e.g. "真实案例")
- Main hook: 4-6 characters (e.g. "别问需求")
- Result promise: 6-12 characters (e.g. "一堆文档变AI工作流")
Never show simultaneously: multiple labels, multiple explanation sentences, multiple process nodes, multiple peer-level titles.
Cover Templates
Template A: Prohibition + Action
别做系统
先跑场景
7天见效
For: enterprise AI, methodology, pitfall-avoidance content.
Template B: Object + Result
一堆资料
变AI工作流
真实案例
For: customer cases, project reviews, data governance content.
Template C: Misconception + Correction
会用AI
不等于提效
先选场景
For: cognitive correction, boss perspective, team efficiency content.
Quality Gates
Fail if:
- More than one main hook competing for attention
- Big text covers the face instead of behind it
- Bottom result is unclear or too long
- Too many explanation sentences
- Cover looks like an information page rather than an attention interceptor
Reference
Read references/cover-sop.md for the full SOP with detailed layer specs, copy extraction methods, and finished cover examples.
