archival-fragments-lite
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseArchival Fragments（简版）
Archival Fragments (Simplified Version)
这个 skill 只固定两件事：这套视觉风格，和参考图 → 首尾帧的做法。
不绑定模型、不装依赖、不代跑流程。你用什么图片模型、什么视频工具都行，只要那个视频工具支持首尾帧。
This skill locks in only two things: this visual style and the reference images → start/end frames method.
There is no model lock-in, no dependency installation, and it does not run the workflow for you. You can use any image model or video tool, as long as the video tool supports start and end frames.
三条硬约束
Three Hard Constraints
违反任何一条，出来的片子必废。这三条都是真实翻过车才写下来的。
Break any one of them, and the finished video will be ruined. These three rules were learned the hard way from real failures.
1. 每一镜的参考图必须不同
1. Every Shot's Reference Image Must Be Different
N 个镜头需要 N+1 张各不相同的参考图。
"相邻两镜共用同一张图"的意思是：第 1 镜的尾帧 = 第 2 镜的首帧，这一张图被这两镜共用。
不是整片共用一张图。
绝对禁止：
- 拿同一张图当所有镜头的输入
- 拿一张结构图、示意图、信息图当所有镜头的参考
- 把 当成生成输入——它是给人看的风格参考板
assets/style-reference.png
真实发生过：Agent 拿一张结构图当所有镜头的参考，结果几十个镜头画面一模一样，整条片子等于一张静态图配了段旁白。
自检：参考图张数 == 镜头数 + 1；任意两张的画面描述不重复；每张有自己独立的提示词。
N shots require N+1 distinct reference images.
“Two adjacent shots sharing the same image” means: Shot 1's end frame = Shot 2's start frame. That one image is shared by the two shots.
It does not mean using one image for the entire video.
Absolutely forbidden:
- Using the same image as the input for every shot
- Using a single structural diagram, schematic, or infographic as the reference for every shot
- Using as a generation input—it is a style reference board for human viewing
assets/style-reference.png
This actually happened: an Agent used a single structural diagram as the reference for every shot, resulting in dozens of shots that all looked exactly the same. The entire video was effectively a static image with a voice-over.
Self-check: number of reference images == number of shots + 1; no two image descriptions are duplicates; each image has its own independent prompt.
2. 具象优先，不要抽象图形
2. Prefer Concrete Subjects Over Abstract Graphics
纸和红线是画面的地面，不是主体。站在上面的必须是观众不用想就懂的具体东西。
给每句话找一个通用符号，全片收敛到 2–3 个，各用几次：
| 语义 | 符号 |
|---|---|
| 谁在哪、份额、从无到有 | 世界地图 + 图钉 + 标签 |
| 价格、代价、失衡 | 天平（一端实物，一端不断加码） |
| 排名、递进、还差多远 | 台阶 / 领奖台 |
| 数量、密集、庞大 | 一大堆实物（芯片、纸片、人群） |
| 时间点、正式性 | 翻牌板、印章、公文 |
| 被否定、被抹掉 | 一只手把东西撕走 / 白纸盖上 |
用空白纸加一条线表达"这个位置是空的"、用三个方块表达"三家公司"——这类抽象图形观众看不懂，实测失败。
The paper and red lines are the ground of the image, not the subject. The things placed on top must be concrete enough for viewers to understand at a glance.
Find a universal symbol for each line of copy, then converge on 2–3 symbols for the entire video, using each several times:
| Meaning | Symbol |
|---|---|
| Who or where, market share, from nothing to something | World map + push pins + labels |
| Price, cost, imbalance | Balance scale (one end holds physical objects, while the other is continuously loaded) |
| Ranking, progression, how much is left | Steps / podium |
| Quantity, density, sheer scale | A large pile of physical objects (chips, sheets of paper, a crowd) |
| Time point, formality | Flip board, stamp, official document |
| Denial, erasure | A hand tearing something away / white paper covering it |
Using blank paper and a line to mean “this position is empty,” or using three squares to mean “three companies”—these kinds of abstract graphics are incomprehensible to viewers and failed in testing.
3. 慢不等于静
3. Slow Does Not Mean Static
每一镜结尾画面必须和开头明显不同。留白镜也要有一个横跨画面的动作在推进。
首尾帧天然帮你守住这条：首帧 ≠ 尾帧，画面必然在变。
Every shot's final frame must be clearly different from its opening frame. Even a negative-space shot needs an action moving across the frame.
Start/end frames naturally enforce this: start frame != end frame, so the image must change.
三步做法
Three-Step Workflow
第一步：拆镜，列出参考图链
Step 1: Break Down the Shots and Map the Reference-Image Chain
把文案按句拆成镜头（每句 2–3 镜），设计一条连续的视觉旅程：
A01 ──W01──> A02 ──W02──> A03 ──W03──> A04 ...这一镜的结束状态，就是下一镜的开始状态。
画面推进只有四种合法方式，每镜必属其一：
| 方式 | 例子 |
|---|---|
| 物件变化 | 地图上零根图钉 → 一根 → 三根 |
| 景别变化 | 世界地图全景 → 推近韩国 → 特写一个钉孔 |
| 状态变化 | 天平上几枚硬币 → 硬币堆成高塔 |
| 主体更替 | 地图退场 → 天平升起 |
拆完先给用户过目——改一张表 5 分钟，重新生成要几小时。
Break the script into shots by sentence (2–3 shots per sentence), and design a continuous visual journey:
A01 ──W01──> A02 ──W02──> A03 ──W03──> A04 ...The end state of one shot becomes the start state of the next.
There are only four legal forms of visual progression. Every shot must fit one of them:
| Method | Example |
|---|---|
| Object change | Zero push pins on a map → one → three |
| Framing change | Wide shot of a world map → push in on Korea → close-up of one pinhole |
| State change | A few coins on a scale → coins stacked into a tall tower |
| Subject replacement | Map exits the frame → balance scale rises into frame |
Show the user the breakdown first—revising a shot list takes 5 minutes, while regenerating it takes several hours.
第二步：出参考图
Step 2: Generate the Reference Images
文生图，一张一个提示词，不挂任何参考图。每张提示词 = 固定风格前缀 + 该张画面。
写法见 keyframes.md，风格前缀在那份文档里。
出完逐张审：文字有没有崩、语义观众看不看得懂、能不能和前后接上。图便宜、视频贵，这一步省不得。
Use text-to-image, with one prompt per image and no reference image attached. Each prompt = fixed style prefix + the content of that image.
See keyframes.md for the format; the style prefix is in that document.
After generation, review each image one by one: whether the text has broken, whether viewers will understand the meaning, and whether it connects cleanly to the images before and after it. Images are cheap, video is expensive, so this step cannot be skipped.
第三步：用首尾帧生成镜头
Step 3: Generate Each Shot with Start and End Frames
每镜挂两张图：第 N 张作首帧、第 N+1 张作尾帧。提示词只写运动，一句话。
写法见 shots.md。
Attach two images to each shot: image N as the start frame and image N+1 as the end frame. The prompt should describe only the motion, in one sentence.
See shots.md for the format.
对工具的要求
Tool Requirements
| 环节 | 要求 |
|---|---|
| 图片 | 能出你要的比例（推荐 4:3），文字渲染较准 |
| 视频 | 必须支持首尾帧——也叫「首尾帧」「first & last frame」「start/end frame」「frames to video」 |
不支持首尾帧的纯文生视频工具做不了这套方法，镜与镜之间必然跳变。
生成时长：多数工具最短 5 秒，而这个风格每镜通常只用 1–3 秒。统一生成 5 秒，剪辑时变速压到目标时长——节奏在剪辑台上定，不在提示词里定。
| Stage | Requirement |
|---|---|
| Image | Can produce the required aspect ratio (4:3 recommended) and renders text accurately |
| Video | Must support start and end frames—also called “first & last frame,” “start/end frame,” or “frames to video” |
Pure text-to-video tools that do not support start/end frames cannot execute this method; transitions between shots will inevitably jump.
Generation duration: most tools have a 5-second minimum, while each shot in this style usually uses only 1–3 seconds. Generate everything at 5 seconds, then adjust the speed in editing to the target duration—the rhythm is set on the editing timeline, not in the prompt.
文档
Documentation
| 文档 | 管什么 |
|---|---|
| style.md | 视觉基线：色板、红色的四种职责、技术标注词汇 |
| keyframes.md | 参考图链设计、风格前缀、图片提示词写法、文字规则 |
| shots.md | 首尾帧运动句写法、动词表 |
examples/assets/example-01..08-*.jpg| Document | What It Covers |
|---|---|
| style.md | Visual baseline: color palette, the four roles of red, technical annotation vocabulary |
| keyframes.md | Reference-image chain design, style prefix, image prompt structure, text rules |
| shots.md | Start/end-frame motion sentence patterns, verb list |
examples/assets/example-01..08-*.jpg