holo-card-studio
Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and a flat white web viewer. Use for 镭射卡、闪卡、全息卡、光栅卡、一念神魔、双形态卡、角色收藏卡,或需要保持角色高度一致的 A/B 状态切换。
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/everettfish--holo-card-studio)HTML
<a href="/listings/everettfish--holo-card-studio"><img src="/api/listings/everettfish--holo-card-studio/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
把这个目录放进 Codex 的 skills 目录即可:
~/.codex/skills/holo-card-studio/
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 95 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: holo-card-studio
- description: Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and a flat white web viewer. Use for 镭射卡、闪卡、全息卡、光栅卡、一念神魔、双形态卡、角色收藏卡,或需要保持角色高度一致的 A/B 状态切换。
- ---
- # Holo Card Studio
- Create a finished collectible card project. The skill has two production routes that share one art direction and one delivery standard.
- ## Route first
- Choose exactly one route before preparing assets:
- - **Holographic foil** is the default route for one character artwork. It uses separate `subject`, `background`, `lineart`, and `text` planes, plus foil and sparkle effects.
- - **Two-image lenticular** is the route for `光栅`, `翻转`, `双图`, `双形态`, or `一念神魔`. It uses two complete card artworks, A and B, and changes the whole card with viewing angle. Do not split one picture into left/right halves and do not fake the two states with SVG.
- If the user asks for 一念神魔, route to lenticular automatically.
- ## Default art direction
- Read [references/art-direction.md](references/art-direction.md) before generating art. Unless the user supplies another style, every generated card uses full-color Japanese ukiyo-e composition with colored sumi-e anime linework: expressive thick-to-thin ink contours, mineral pigments, visible brush texture, dramatic movement, and a coherent illustrated environment.
- For a two-state card, generate A first, then edit A into B with the image-generation tool. Repeat the identity and composition invariants in the edit prompt. Keep the same face structure, hair/fur, costume anchors, proportions, camera, crop, body scale, and major silhouette. Expressions must clearly communicate the state: the benevolent state is serene, compassionate, and resolute; the malevolent state has focused predatory eyes, sharper brows, and a controlled feral or cruel expression without changing identity.
- Foil and diamond sparkle are presentation layers, not substitutes for artwork. Default `foil` and `particles` to `1.0`; keep the face readable and preserve the ink contours.
- ## Generate images
- Use the built-in image-generation tool for raster artwork. Do not ask the user to generate the images elsewhere. Do not use SVG or procedural stand-ins when a final illustration is requested.
- For no-reference generation:
- 1. Generate the complete A artwork from the character brief using the default style.
- 2. Generate B by editing A. Lock identity, framing, and major geometry; change the expression, state-specific costume details, lighting, atmosphere, and action effects.
- 3. Save both as portrait PNG files with identical dimensions.
- For reference-driven generation, treat the reference as the identity source and A as the direct adaptation. Then edit A into B. Read [references/lenticular-route.md](references/lenticular-route.md) for the required prompt structure and alignment checks.
- ## Build the project
- Create a user-owned project directory outside this skill. Copy the matching example config and prepare its assets.
- Holographic assets:
- ```text
- assets/subject.png
- assets/background.png
- assets/lineart.png
- assets/text.png
- card-config.json
- ```
- Lenticular assets:
- ```text
- assets/image_a.png
- assets/image_b.png
- assets/text.png
- card-config.json
- ```
- Run the shared dispatcher:
- ```powershell
- python scripts/run_pipeline.py --project <project-dir> --mode holographic
- python scripts/run_pipeline.py --project <project-dir> --mode lenticular
- ```
- `--mode` may be omitted when `card-config.json` contains `"mode"`. The default is `holographic`.
- For lenticular projects, run `scripts/lenticular/prepare_pair.py` before the pipeline when normalization or an alignment report is needed. The pipeline creates typography when `text.png` is absent, validates assets, builds `card.blend`, renders previews, exports `web/assets/card.glb`, copies the matching web viewer, and installs its local web dependencies unless `--skip-npm` is supplied.
- ## Verify and deliver
- Read [references/verification.md](references/verification.md). At minimum verify:
- - the Blender scene contains physical card depth and multiple effect planes;
- - A and B replace the entire illustrated face and remain recognizable as one character;
- - front and angled renders show a readable state change;
- - foil, glitter, line glow, and lenticular ridges are visible without washing out the face;
- - the white web viewer loads the GLB and supports pointer/touch tilt without horizontal overflow.
- Deliver the source images, `card.blend`, renders, web viewer, and a validation report. Keep generated binaries in the project, never inside the reusable skill archive.
- ## References
- - [references/art-direction.md](references/art-direction.md): shared default style and prompt recipes.
- - [references/holographic-route.md](references/holographic-route.md): multilayer foil-card workflow.
- - [references/lenticular-route.md](references/lenticular-route.md): full-image A/B workflow and identity lock.
- - [references/config.holographic.example.json](references/config.holographic.example.json): single-art config.
- - [references/config.lenticular.example.json](references/config.lenticular.example.json): two-state config.
- - [references/lenticular-model.md](references/lenticular-model.md): view-angle model.
- - [references/verification.md](references/verification.md): render and browser acceptance checks.
README.md · README · 208 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # 🃏 Holo Card Studio
- [English](README.en.md)
- 实现教程来源(感谢大佬!):小红书@乌托邦的香蕉🍌
- > 一个 **Codex Skill**:对 Codex 说一句话,收获一张会随视角流光溢彩的 3D 全息闪卡。
- > 能在浏览器里拖着转、翻到背面、拉滑块看它闪;还附赠一个可以随便改的 Blender 工程。
- 小时候在文具店门口舍不得买的那种闪卡,现在你想印谁就印谁。
- ---
- ## ✨ 三十秒看懂
- ```
- 你:「给我做一张赛博朋克风的机械猫闪卡,背景霓虹雨夜,编号 No.007」
- Codex:
- 🎨 画好四层图(主体 / 背景 / 线稿 / 文字)
- 🧊 搭好 Blender 场景,视差、镭射、星光一次到位
- 🌐 组装成 Three.js 网页,本地跑起来
- 📦 递给你:网页链接 + card.blend + 渲染图
- ```
- 你只负责想,剩下的它来。
- ---
- ## 🎬 你可以拿它做什么
- ### 🐱 给自家毛孩子发一张"传说级"卡
- 上传一张猫主子的照片,加一句"传说稀有度、金色边框、名字叫布丁"。
- 主体保留它本猫的神态和构图,背景和线稿全新绘制。拖一拖,猫在卡里往前凸,背景往后退,镭射彩虹随角度流动——朋友圈晒图请自便。
- ### 🎮 给独立游戏做角色卡牌
- 一个角色一句描述,批量出一整套:战士、法师、盗贼、Boss。
- 每张卡自带 `card-config.json`,稀有度、编号、属性文字都在里面,改完重新跑一遍流水线就更新。发售前发一波"抽卡预告",玩家会疯。
- ### 🏢 团队周年纪念 / 新人入职卡
- 把同事做成卡牌:头像当主体、部门色当背景、Slogan 当文字层。
- 每人一张,网页链接一发,大家在浏览器里翻自己的卡翻一下午。比 PPT 里的"团队介绍"页好玩一百倍。
- ### 🎁 情人节 / 生日 / 纪念日
- "复古胶片风、粉金配色、背面写一句话"。
- 做好之后发一个链接过去,对方在手机上转着看,翻到背面看到那句话。仪式感这东西,闪光效果拉满就有了。
- ### 🎤 演讲 / 发布会的"彩蛋物料"
- 产品发布做一张产品卡,讲到最后一页丢一个链接:"扫码看会闪的那种"。
- 响应式网页,手机横竖屏都能玩,观众当场就转起来了。
- ### 🖌️ 设计师的材质实验场
- 不只是网页,`card.blend` 是真正可编辑的 Blender 工程。
- 共享节点组里有中文命名的 `缩放`、`深度`、`视差效果`,镭射条纹、星光、线稿发光都是独立可调的材质节点。想研究全息卡是怎么"闪"起来的,打开它就是最好的教材。
- ---
- ## 🧱 一张闪卡是怎么叠出来的
- 四层图叠在同一块画布上,视差把它们在空间里"撑开":
- ```
- 👀 你的视线
- │
- ┌─────┴──────┐
- │ text.png │ 文字层 ─ 稳稳贴在表面
- ├────────────┤
- │ lineart.png│ 线稿层 ─ 发光的轮廓
- ├────────────┤
- │ subject.png│ 主体层 ─ 往前凸出来
- ├────────────┤
- │ background │ 背景层 ─ 往后缩进去
- └────────────┘
- ```
- 再铺上镭射彩虹(相位跟着视角走,转到哪闪到哪)、Voronoi 星光、金色卡边。
- 浏览器端用 Three.js 按同一套 UV 公式重建这四层合成,呈现相同类型的视差和镭射效果;网页着色与 Blender 离线灯光不同,颜色、辉光和背面装饰会有差异。
- 镭射卡默认查看器采用纯白无边框画布、黑色无衬线排版和扁平控件,只保留卡片标题、直接操作与材质/景深滑杆,让卡片本身成为视觉中心。
- ---
- ## 🚀 怎么用
- ### 安装
- 把这个目录放进 Codex 的 skills 目录即可:
- ```
- ~/.codex/skills/holo-card-studio/
- ```
- ### 环境
- - Python 3 + Pillow
- - Node.js + npm
- - Blender **不用自己装** —— 流水线会自动把官方便携版放到 `<project>/tools/`,校验 SHA-256,项目自带、互不干扰
- 已有 Blender 时会优先复用,也可用 `--blender` 指定可执行文件。全息路线适配旧版合成节点和新版合成节点组,macOS 可使用 Metal;偏好设置保存在项目的 `tools/blender-config/`。
- 准备好素材与配置后,可以直接运行:
- ```sh
- python scripts/run_pipeline.py --project <project-dir> --mode holographic
- ```
- 不写 `--mode` 时读取配置中的 `mode`,配置也没有时默认 `holographic`。`--skip-render` 跳过静态渲染,`--skip-npm` 跳过网页依赖安装。查看[验收说明](references/verification.md)了解实际运行、渲染和浏览器检查的范围。
- ### 开口
- 然后在 Codex 里直接说人话:
- > "用 holo-card-studio 给我做一张水墨风的锦鲤闪卡,文字用书法体,编号 No.001"
- 或者上传参考图:
- > "照这张图做一张闪卡,保留人物和构图,背景换成星空"
- Codex 会先把卡片规格和它推断的细节说给你听,然后开工:画图 → 生成文字层 → 写配置 → 跑流水线 → 起本地服务 → 真正打开页面测拖拽、翻面、滑块和手机布局 → 交付。
- ### 你会收到
- | 东西 | 用来干嘛 |
- |---|---|
- | 本地网页链接 | 拖、转、翻、拉滑块 |
- | `card.blend` | 在 Blender 里继续调材质、换灯光、出渲染 |
- | `assets/` 四层图 | 想换哪层换哪层,重跑流水线即可 |
- | `card-config.json` | 改名字、改编号、改稀有度 |
- | 渲染图 | 直接发 |
- ### 多张卡:自动分类展厅
- 需要持续生成和分发多张卡时,可以把每张流水线产物归档为独立目录,再由清单生成器汇总成瀑布流展厅。每张卡保留永久 URL,主页则按人物、风格、主题和稀有度自动生成筛选项。
- - 在线示例:<https://card.waterq.us/>
- - 配套项目:<https://github.com/chenweilie/holo-card-gallery>(私有仓库,需要所有者授权)
- - 接入规范:[多卡展厅与自动分类](references/gallery-distribution.md)
- ---
- ## 🔧 可以调的旋钮
- 流水线出厂就是一套顺手的参数,也都留了口子:
- - **视差强度**:主体默认 scale 1.25 / depth 0.4,背景 depth -0.25,想更"跳"就往上加
- - **镭射条纹**:条纹密度、扭曲度、角度,以及粉-黄-蓝-白的渐变
- - **线稿发光**:强度和遮罩密度,可以从"淡淡勾边"到"霓虹描边"
- - **星光**:Voronoi 尺度 + 动画噪声,从零星几颗到满天星
- - **Blender 界面语言**:默认简体中文,存在项目本地配置里,一句话可换
- ---
- ## 📁 目录一览
- ```
- holo-card-studio/
- ├── SKILL.md # Codex 读的"操作手册"
- ├── references/
- │ ├── art-direction.md # 分层画图的提示词写法、参考图处理
- │ ├── config.example.json # 卡片配置示例
- │ └── verification.md # 交付前的验收清单
- ├── scripts/
- │ ├── ensure_blender.py # 自动获取官方 Blender 便携版
- │ ├── build_card.py # 生成可编辑的 Blender 场景
- │ ├── export_web.py # 导出卡片几何
- │ ├── generate_typography.py # 精确的透明文字层
- │ ├── validate_assets.py # 四层图体检
- │ ├── run_pipeline.py # 一键流水线
- │ └── package_skill.py # 纯文本打包成可分享的 ZIP
- └── assets/
- └── web-template/ # 响应式 Three.js 查看器
- ```
- skill 本体只有代码和文字,轻得很。你生成的画作、`.blend`、模型都待在你自己的输出项目里。
- ---
- ## 🤝 分享这个 skill
- 想发给朋友或放进仓库?
- ```bash
- python scripts/package_skill.py
- ```
- 它按白名单只打包文本文件,打出来的 ZIP 干干净净,拿走就能用。
- ## 🔀 新功能:双图光栅卡
- 现在除了原有的单图全息镭射卡,还可以制作光栅卡、翻转卡、双形态卡和一念神魔。
- 这条路线使用两张**完整卡面**:A 图与 B 图会随观看角度切换整张画面,不是把一张图切成左右两半。无参考图时默认采用全彩日式浮世绘构成与水墨动漫勾线;有参考图时先生成 A,再以 A 为身份锚点编辑出 B,锁定脸型、比例、服装锚点、镜头与主体尺度。
- Blender 工程包含实体卡基、图像层、柱镜光栅、镭射膜、轮廓光、闪钻粒子等独立层。网页加载 Blender 导出的 GLB,用同一套视角公式驱动整卡切换,并支持鼠标与触控倾斜。
- ~~~bash
- python scripts/run_pipeline.py --project <project-dir> --mode lenticular
- ~~~
- 光栅项目使用:
- ~~~text
- assets/image_a.png
- assets/image_b.png
- assets/text.png
- card-config.json
- ~~~
- 流水线会交付 card.blend、正视/倾斜渲染、web/assets/card.glb、白底 Three.js 查看器和验证报告。原有全息路线继续使用 --mode holographic,也可以通过 card-config.json 的 mode 自动选择。
- ---
- *想好第一张卡画谁了吗?* ✨
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.