Scene Blocking Consistency logo

Scene Blocking Consistency

Community
SwotAtmk
scene-blocking-consistency

人物/道具站位一致性:为每个场景建立「站位表」(空间锚点+角色默认方位+道具锚点+180度轴线与允许机位),并强制同一场景内所有镜头的 sub_shots / visual / video_prompt 复述并保持人物/道具相对左右方位、朝向、视线一致,消除跨镜左右漂移。当出现人物在左、下一镜位置关系错乱、左右漂移、站位不连贯、越轴等分镜一致性问题时使用。

Overview

PublisherSwotAtmk
Repositoryinfinite-creation
Skill namescene-blocking-consistency
Stars
112
Forks
30
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SwotAtmk on GitHub. Read the source before you install it.

Installation

Install the Scene Blocking Consistency AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SwotAtmk/infinite-creation/tree/main/skills/scene-blocking-consistency
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SwotAtmk/infinite-creation.git /tmp/infinite-creation
mkdir -p .claude/skills
cp -r /tmp/infinite-creation/skills/scene-blocking-consistency .claude/skills/scene-blocking-consistency
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Scene Blocking Consistency in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Scene Blocking Consistency on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Scene Blocking Consistency is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

人物/道具站位一致性(scene-blocking-consistency)

把「站位」当成与人物外貌、服装、画风同级的一致性锚点来管理。核心思想:先为每个场景定一张站位表(blocking map),之后同一场景内所有镜头一律从这张表取方位,禁止逐镜自由发挥导致左右关系漂移。

何时使用

  • 拆分镜前、写视频提示词前,凡涉及多人同场、人物与道具同框的场景,都必须先建立/读取站位表。
  • 排查「上一镜人物在左、下一镜跑到右」「两人对视方向相反」「道具从左边瞬移到右边」等问题时,按本技能重建站位表并逐镜校正。

站位表结构(每个场景一条)

站位表写进 bible.md 的「场景站位表」章节。每张表包含四块:

【场景 01】图书室·黄昏
- 空间锚点:门=画面左;窗=画面右;书桌=画面中偏左;书架=画面右后
- 角色站位:
  - 林默:画面左侧,面向右(朝向苏婉),距门约1步
  - 苏婉:画面右侧,面向左(朝向林默),背对窗
- 道具锚点:
  - 茶壶:书桌上,位于两人之间偏左
- 轴线与机位:以「林默—苏婉」连线为轴线;机位统一在轴线下方(两人正前方偏左),禁止越轴

字段说明

字段含义必填
空间锚点场景内固定参照物(门/窗/桌/床/台阶/柜台…)相对画面的左右/前后方位是
角色站位每个入镜角色相对锚点的方位 + 朝向(面向左/右/前/背对镜头)是
道具锚点关键道具相对角色/锚点的方位(尤其会被拿取/强调的道具)有道具时必填
轴线与机位角色连线的轴线,及本场景允许的机位侧(统一同侧)多人同场时必填

六条铁律

  1. 180 度轴线规则:同一场景内,机位必须始终保持在角色连线(轴线)的同一侧;确需越轴时,必须先用一个「全景/两人同框」镜头交代,或让角色走位自然换边,否则禁止直接越轴。
  2. 屏幕方向一致:同一角色在连续镜头中位于画面的左右侧保持一致(画面左/画面右),除非剧情明确要求其走位移动,且该移动路径在镜头里被写清。
  3. 视线匹配:面对面对话时,一方看向左、另一方看向右;视线方向跨镜一致,不得出现两人同看一边的「镜像跳」。
  4. 道具锚点一致:道具相对角色/场景锚点的方位跨镜一致(桌上的茶壶始终在两人之间偏左),不得瞬移。
  5. 换位/走位必须显式交代:若剧情要求角色换位(起身、走到窗边、绕到对方身后等),必须在该镜头的 sub_shots 里写清「起点→路径→终点」,并更新站位表为新站位;换位之后的镜头沿用新站位。
  6. 镜头间上下文承接(先判断转场,再决定是否参考):写分镜 N 前,先比较它与分镜 N-1 的 scene_name/场景头与时间——同一场景且时间连续 → 必须参考站位:分镜 N 起幅 = 分镜 N-1 落幅(角色左右方位、朝向、道具位置、动作方向一致);发生转场(场景头变化/地点切换/时间跳跃/淡入黑场等)→ 不参考上一镜位置,为新场景重建站位表。

执行步骤

1. 拆分镜前:建立/读取站位表

  • 先按场景聚合本章,为每个场景建立站位表(见「站位表结构」)。
  • 若 get_project 返回的 context.bible 里已有该场景的「场景站位表」,直接沿用;剧情走位变化时才更新。

2. 持久化到 bible(注意覆盖式写入)

  • bible 是覆盖式写入:先 get_project 读回现有 context.bible,把「场景站位表」章节合并进全文(保留已有的人物外貌/衣橱等内容),再 save_context('bible', 合并后的全文)。
  • 站位表按场景分条,随剧情推进可追加新场景、更新走位后的旧场景。

3. 写分镜时复述站位(含镜头间承接)

  • 每条 set_storyboard 的 visual 与 sub_shots 必须明确写出「角色X在画面左/右、面向左/右、距某锚点远近」,不写「同上/保持原样」这类零指代。
  • 子分镜之间若有人物走位,写清移动路径与起终点。
  • 先判断是否转场:写分镜 N 前,比较它与分镜 N-1 的 scene_name/场景头与时间。同场景且时间连续 → 参考站位(承接上一镜落幅);发生转场(场景切换/地点变化/时间跳跃)→ 不参考上一镜位置,为新场景重建站位表。
  • 按 idx 顺序逐条写分镜:同场景连续时,写第 N 条前先回顾第 N-1 条 sub_shots 的结尾一段(落幅),第 N 条的起幅站位承接第 N-1 条的落幅;续跑追加时用 list_shots 读回已有分镜的最后落幅再接写。

4. 写视频提示词时复述站位(英文)

  • 写 video_prompt 时,把站位表方位翻译成英文并复述进每个镜头,例如 Lin Mo stands on screen-left facing right; Su Wan stands on screen-right facing left。
  • 参考标签(__MINIMAX_H3_REF_N__)与站位描述并存,互不替代。

常见错误(写分镜时自查)

  • 越轴:两人对话,A 镜从左侧拍、B 镜突然从右侧拍,导致人物左右互换。
  • 镜像跳:同一场景两人对望,却都写成「面向右」或都「面向左」。
  • 道具瞬移:上一镜茶壶在两人之间,下一镜跑到窗边。
  • 零指代:sub_shots 写「人物位置保持原样」,但没写「原样」具体是什么。

详见 references/blocking-map.md(模板与示例)与 references/continuity-rules.md(规则判定细节)。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Scene Blocking Consistency AI skill do?

人物/道具站位一致性:为每个场景建立「站位表」(空间锚点+角色默认方位+道具锚点+180度轴线与允许机位),并强制同一场景内所有镜头的 sub_shots / visual / video_prompt 复述并保持人物/道具相对左右方位、朝向、视线一致,消除跨镜左右漂移。当出现人物在左、下一镜位置关系错乱、左右漂移、站位不连贯、越轴等分镜一致性问题时使用。

Why use Scene Blocking Consistency on TypingMind?

Because you install it once and use it with any model. Scene Blocking Consistency is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Scene Blocking Consistency in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SwotAtmk/infinite-creation/tree/main/skills/scene-blocking-consistency. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Scene Blocking Consistency?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Scene Blocking Consistency?

As many as you like. As long as a model supports skills, you can use Scene Blocking Consistency with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Scene Blocking Consistency AI skill free?

Yes. It is published on GitHub by SwotAtmk under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇