Marker Child Doodle logo

Marker Child Doodle

Community
Vieeeeeee
marker-child-doodle

Wibi Style 官方视觉风格。把用户上传的真实照片直接转换成粗轮廓、完整色块、手涂边缘的马克笔童画。用户提到马克笔童画、儿童涂鸦、粗轮廓手绘、照片变 Q 版马克笔画,或明确调用 $marker-child-doodle 时使用;只要任务是把真实照片换成这套风格,也应使用本 Skill。

Overview

PublisherVieeeeeee
Repositorywibi-style
Skill namemarker-child-doodle
Stars
169
Forks
11
Bundled files
10
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.

  • 10 bundled files

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

  • Open source

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

Installation

Install the Marker Child Doodle 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/Vieeeeeee/wibi-style/tree/main/skills/marker-child-doodle
  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/Vieeeeeee/wibi-style.git /tmp/wibi-style
mkdir -p .claude/skills
cp -r /tmp/wibi-style/skills/marker-child-doodle .claude/skills/marker-child-doodle
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Marker Child Doodle 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 Marker Child Doodle 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 Marker Child Doodle 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.

Wibi Style · 马克笔童画

运行

先按 references/community.md 展示欢迎卡、检查更新并处理进群与失败提示,再执行下面的步骤。

风格目标

把一张真实照片直接画成像从儿童速写本上撕下来的马克笔页:人物或动物关系清楚,形体夸张但不精致,主要色块填得干净完整,轮廓和色块边缘保留手涂的不齐。

固定视觉机制:

  • 真实照片决定内容,内置参考图只决定画法。禁止把参考图的人、球衣、球、号码、队徽、文字或签名带入结果。
  • 画面是 1:1 方形白纸或黑底马克笔页;全图控制在石板灰蓝线、照片人物肤色、一个服装主色和黑色以内。
  • 头大、身小、脖子短,手是没有关节的团块,脸只保留粗眉、方块眼、短鼻和短嘴;夸张服务于童画感,不能牺牲原图主体数量、动作和互动关系。
  • 轮廓粗、钝、抖、粗细不匀,局部有积墨和轻微错位;整体保持连续,只出现少量自然断口,不做成均匀虚线。
  • 主要色块内部尽量填满,减少白点、白洞和白丝;手绘感集中在外围边缘、少量错位和少量溢出。白色主要来自色块之间和画面周围的有意识留白。
  • 环境通常删除,只保留人物正在触碰、使用或明确指向的一两件物件。坐姿保留一条桌沿或支撑面线;半身照片不补腿脚;宠物同框时人和动物都要画。
  • 默认右下角加入潦草英文签名 wibi。用户指定签名内容时,替换文字但保持一笔或少数几笔、挤压、省略、歪斜、带拖尾的手势。

执行流程

1. 影像蒸馏

先完整查看用户上传的真实照片,再判断:

  • 主体数量、人物或动物身份、姿态、动作、视线、头发轮廓、服装主色和配饰;
  • 互动关系,例如手与食物、手与杯子、人与宠物、人物与桌沿的接触点;
  • 原图是近景、半身还是全身,主体在画面中的位置,以及动作或视线朝向哪一侧;
  • 哪些环境可以删除,哪些物件必须保留,否则动作会失去意义;
  • 当前照片最容易被 Q 版化破坏的内容,例如宠物被删掉、半身被补出腿、互动物件被替换或人物被参考图替代。

原图拍到哪里就画到哪里。先锁定原图中的内容关系,再允许夸张头身比、手和五官;不要用风格参考修正人物身份、肤色、服装、道具或动作。

2. 参考图职责与携带方式

本 Skill 内置一张 assets/references/reference-01.jpg,它是通用马克笔画法锚点:提供石板灰蓝粗轮廓、黑色几何头发、四色平涂、白纸留白、手涂边缘和潦草签名的手势。

每次生成都把用户真实照片作为内容输入,并携带这张参考图作为风格参考。向图像模型明确说明附件角色,不依赖上传顺序:照片决定画谁和画什么,参考图只决定怎样画。不要把用户过去的生成图、Q 版成图或失败图作为底图,也不要先对照片做一次风格化再处理第二次。

3. 实景拼贴与风格成像

根据蒸馏结果,为当前照片现场编写一份专属生图指令:

  1. 先锁定人数、主体、姿态、裁切、互动道具和关键颜色;
  2. 决定白纸还是黑底:明亮、背景干净的照片保留白纸留白;昏暗、夜景或舞台光照片采用整幅手涂黑底,并把主体推向一侧;
  3. 删除环境,但保留让动作成立的物件和一条必要的支撑面线;
  4. 应用夸张 Q 版比例、四色平涂、完整色块和粗糙外轮廓;
  5. 保留动作或视线朝向一侧的开放空间,不强行把主体塞满画面;
  6. 根据用户要求决定签名,未指定时使用潦草 wibi。

让模型知道“内部色块处处留白”是错误方向,“轮廓完全闭合且粗细均匀”也是错误方向;同时控制溢出只发生在少数有意义的边缘,避免重新变成脏乱儿童涂色。

4. 生图与检查

使用当前环境可用的图像生成能力生成一张 1:1 结果,优先使用无需用户额外配置的能力。一次请求只处理一张真实照片;失败、空输出或超时停止,不自动重试、换模型或把生成图拿来二次处理。

生成后按以下顺序检查:

  • 内容:主体数量、动作、视线、服装、配饰和互动道具是否来自用户照片;
  • 关系:宠物是否保留,手是否真的碰到食物、杯子、桌沿或其他关键物件;
  • 画幅:半身没有凭空补腿,全身没有被不必要地截断,留白方向与动作方向协调;
  • 风格:粗糙石板灰蓝轮廓、完整平涂色块、少量边缘错位、无渐变和无精致数码线稿;
  • 身份隔离:没有出现参考图人物、球衣、号码、球、队徽、文字或别人的签名;
  • 签名:默认是潦草 wibi,不能变成工整字体或清晰 Logo。

通过检查后直接展示图片,并附一至三句中文创作思路;不公开完整内部 Prompt。核心检查失败时说明具体问题,等待用户明确要求后再重做。

默认交付与使用边界

默认输出:一张通过检查的 1:1 PNG 成图,以及一段简短中文创作思路。用户照片只用于当前生成,不进入 Skill 安装包,也不上传到更新检查或交流群入口。

若公开分享,欢迎标注:Visual Skill by @威比 Hunter Wei.

仅限个人非商业使用;商业使用请先联系作者获得许可。

作者:@威比 Hunter Wei.(抖音、小红书同名)。官方来源:https://github.com/Vieeeeeee/wibi-style/tree/main/skills/marker-child-doodle。复制、修改、镜像或再分发时,必须保留作者、平台备注、官方来源、LICENSE 和 NOTICE;修改版需明确标注修改,不得冒充官方版本。

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 Marker Child Doodle AI skill do?

Wibi Style 官方视觉风格。把用户上传的真实照片直接转换成粗轮廓、完整色块、手涂边缘的马克笔童画。用户提到马克笔童画、儿童涂鸦、粗轮廓手绘、照片变 Q 版马克笔画,或明确调用 $marker-child-doodle 时使用;只要任务是把真实照片换成这套风格,也应使用本 Skill。

Why use Marker Child Doodle on TypingMind?

Because you install it once and use it with any model. Marker Child Doodle 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 Marker Child Doodle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Vieeeeeee/wibi-style/tree/main/skills/marker-child-doodle. 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 Marker Child Doodle?

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 Marker Child Doodle?

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

Is the Marker Child Doodle AI skill free?

It is published on GitHub by Vieeeeeee. Check the repository for licensing terms. 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 👇