Fantasy Character Visual Dna logo

Fantasy Character Visual Dna

Community
dacnay816y62-hub
fantasy-character-visual-dna

Design distinctive fantasy characters and construct character base images through available image tools, paired with matching Midjourney prompts for further visual development. Use for 角色设计, 神话二创, 角色底图, 角色反推, MJ/Image2/Banana角色提示词, focused character edits and consistent character assets. The gallery was created with MJ + Image2, not by this Skill alone. Preserve prompt-only requests and the user's chosen style; exclude unrelated retouching, typography and interior rendering.

Overview

Publisherdacnay816y62-hub
Repositoryfantasy-character-visual-dna-skill
Skill namefantasy-character-visual-dna
Stars
64
Forks
8
Bundled files
29
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.

  • 29 bundled files

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

  • Open source

    Published by dacnay816y62-hub on GitHub. Read the source before you install it.

Installation

Install the Fantasy Character Visual Dna 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/dacnay816y62-hub/fantasy-character-visual-dna-skill/tree/main
  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/dacnay816y62-hub/fantasy-character-visual-dna-skill.git \
  .claude/skills/fantasy-character-visual-dna
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fantasy Character Visual Dna 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 Fantasy Character Visual Dna 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 Fantasy Character Visual Dna 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.

FANTASY CHARACTER VISUAL DNA

把角色身份、身体结构、服装与标志物组织成可辨识、可继续开发的视觉形象。默认采用电影级写实;用户明确指定的风格优先。

0. 先说明定位与交付结构

本 Skill 负责人物形象设计与底图构建。图库全部 19 张示例图由作者使用 MJ + Image2 生成与完善,不是 Skill 单独生成的最终画面。 不把示例包装成一键直出效果,也不虚构逐图生成过程或参数。

完整交付结构:生成角色底图 + 配套 MJ 提示词。 在新用户首次完整角色设计的开头,用一句短提示让其看到:人物形象设计 → 角色底图 + MJ 提示词 → MJ 视觉深化 → Image2 修正与完善。 后续局部修改不反复插入长说明;严格“只要提示词”等输出要求优先。

  • 完整新角色设计默认构建一张便于观察人物的底图,并交付同设定的 MJ 提示词;实际图像由当前环境提供的图像工具生成。
  • 只要提示词时不调用图像工具;只要图片、指定平台或指定语言时按用户要求交付。
  • 没有图像工具时,明确说明“角色底图尚未生成”,提供底图生成说明与 MJ 提示词,不把一段文字标成已生成的图片。
  • 底图优先解决角色身份、比例、脸、服装与标志物的可辨识性;后续画面风格、表现与完善交给 MJ + Image2 工作流。其他工具可按用户选择替代,不改写图库来源。

1. 先选择当前任务

用户要什么执行方式按需读取
一个新角色或神话重构明确身份与少量核心识别点,以角色底图 + MJ 提示词交付一版主方案设计规则、提示词编译
根据图片反推或局部修改分配参考图用途,保留身份与未修改区域参考与编辑
MJ / Image2 / Banana 提示词仅交付所需语言和平台的可复制文字提示词编译
三视图、头肩、表情或道具资产使用已确认基准,只改变本次允许的变量资产一致性
系列角色或群像先建立角色差异,再统一材料工艺与世界观设计规则
已确认的赛博西游项目在通用规则上加载对应角色预设赛博西游预设
反馈修改或结果检查定位具体问题,最小范围修正质量与纠偏

只读取本次需要的参考。规则文件是执行依据;示例图库是视觉案例,不是所有新角色必须照搬的模板。

2. 保留用户意图

在系统与执行环境约束内,依次采用:当前明确要求和最新修正、已确认角色基准、当前项目设定、本 Skill 默认值。

  • 新要求只覆盖对应字段,不重写其他已确认内容。
  • 风格参考不自动成为身份参考;局部服装参考不自动替换人脸、姿态和背景。
  • 完整角色设计按第 0 节交付;用户只要提示词时只输出文字,不擅自生成图像。
  • 不声称已经操作无法访问的 Midjourney、Image2、Banana 或其他平台;提供 MJ 提示词不等于已完成 MJ 生成。
  • 输入基本足够时直接完成一版主方案。仅当关键身份、基准版本或硬性要求相互冲突且无法判断时询问。
  • 不自动扩成完整世界观、多轮问卷、批量变体或全套资产。

3. 建立视觉 DNA

从输入中确定身份与处境、种族、身体比例、面部毛发、服装材质、核心道具、姿态、镜头背景和画幅。只补充这次任务必需的信息。

先保留 1–3 个关键识别点,再发展少量创新。把“高级、神秘、赛博、暗黑”等词落实成轮廓、结构、材质或动作,避免只有形容词。

设计时检查:

  1. 身份与物种。 完整兽妖拥有相容的头部、颈肩、躯干与四肢逻辑,不能退化为普通人戴动物鼻子。写实不等于人类化。
  2. 独立轮廓。 不把全员都设计成宽肩、肌肉、披风、大腰带、尖刺装甲;角色差异应在缩小后仍然可见。
  3. 脸与性格。 通过骨相、年龄、比例、眼神和细微不对称区分新角色,避免网红脸、仙侠手游脸与统一精致美人脸。保持参考人物时不得借此换脸。
  4. 可理解的衣物与道具。 写清层次、连接、厚薄、受力和用途,不以随机首饰替代设计。
  5. 细节有主次。 聚焦脸、核心道具与少量识别区域,其余位置保留完整安静面。干净意味着减少噪点和碎饰,而非抹掉材质。
  6. 磨损有原因。 让使用痕迹发生在合理接触与受力部位,不用全身泥锈与破布代替真实感。
  7. 文化与科技有边界。 科技元素只在需要时加入,并服务身份、能力或功能。赛博西游不是全题材默认;西方角色不自动添加佛珠、经文或天庭装甲。

用户主动要求华丽、夸张、插画或动画风时遵循该方向,继续保持身份、结构与信息主次,不把默认审美当作否决理由。

4. 让画面服务任务

  • 看脸用头肩或胸像,看衣服用三分之二身,看轮廓与完整道具用全身。
  • 明暗与光线要支持辨识,不能让烟、特效、黑暗和背景吞没核心信息。
  • 单角色通常使用低信息密度背景,1–2 个环境提示即可;叙事图可以按情节扩充。
  • 动作具有落脚、重心、握持与衣物响应,不用同一姿态套所有角色。
  • 画幅服从用户与已确认项目约定。未指定时,可用 3:4 展示单角色,用 16:9 组织三视图或表情板;这些是建议。
  • 新角色资产默认无文字。题字、红印章、Logo 与信息栏仅在用户要求时加入,不从示例图自动复制。

5. 锁定参考和资产

区分用户明确要求、图片可见事实与设计推定。反推不等于恢复原始提示词;未展示区域不等于已经被还原。

选定基准后记录:身份、物种与比例、脸型五官、发型发色、服装层次配色、饰物所在侧、武器结构数量、不可改变部位。左右以角色自身为准,必要时补充画面位置。

三视图共享比例和尺度,只改变观察角度;表情图只改变合理肌肉状态;局部编辑只修改目标区域。对未展示的背面结构提出相容设计时,标明推定,确认后再纳入基准。

用户要求九齿、九珠、多头等准确数量时,提示词应安排足够可见性,并在实际输出中计数。被遮挡或看不清不能报告“完全一致”。

6. 编译交付

按身份 → 身体 → 面部毛发 → 服装材质 → 标志物 → 动作 → 构图光线 → 必要限制组织提示词;删除重复空泛词。

  • 中英提示词共享同一设定;按用户需要给单语言或双语言,不擅自加武器、颜色和身份。
  • 平台主体描述与参数分开。具体版本号、参考参数和权重仅在已确认支持时填写;无法核实时交付主体文本并说明参数尚未确认。
  • 编辑指令明确底图、保留项、修改对象、参考分工及光线遮挡衔接,不在局部修改时同时重做整个角色。
  • 完整角色设计交付简短定位、实际生成的角色底图及配套 MJ 提示词;两者共享相同的身份、体型、脸、毛发、服装、配色和标志物。底图出现偏差时先修正或明确待修项,不让提示词悄悄成为另一个角色。
  • 用户要求精简或仅提示词时省去设计分析,并遵循指定平台与语言;用户要求完整方案时再展开 DNA 与设计理由。

7. 检查与结束

对照当前请求检查身份锚点、物种结构、参考分工、角色差异、道具关系、图文一致与输出格式。

收到反馈时把问题转成具体可见操作,保存已确认内容,优先修正出错部位。实际生成图像后依据图像检查;纯文字任务只能报告文字检查,不能宣布画面测试通过。

达到用户要求后交付,不自动开始新的批次。保留对模型限制与未验证项目的准确说明,避免绝对一致或一键复现承诺。

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 Fantasy Character Visual Dna AI skill do?

Design distinctive fantasy characters and construct character base images through available image tools, paired with matching Midjourney prompts for further visual development. Use for 角色设计, 神话二创, 角色底图, 角色反推, MJ/Image2/Banana角色提示词, focused character edits and consistent character assets. The gallery was created with MJ + Image2, not by this Skill alone. Preserve prompt-only requests and the user's chosen style; exclude unrelated retouching, typography and interior rendering.

Why use Fantasy Character Visual Dna on TypingMind?

Because you install it once and use it with any model. Fantasy Character Visual Dna 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 Fantasy Character Visual Dna in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dacnay816y62-hub/fantasy-character-visual-dna-skill/tree/main. 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 Fantasy Character Visual Dna?

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 Fantasy Character Visual Dna?

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

Is the Fantasy Character Visual Dna AI skill free?

It is published on GitHub by dacnay816y62-hub. 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 👇