Fisheye Motion logo

Fisheye Motion

OrganizationPopular
vibe-motion
fisheye-motion

制作屏摄风格的鱼眼畸变效果与聚焦动画：桶形鱼眼畸变 + 细扫描线/摩尔纹干涉 + 四周暗角， 可对任意图片/视频做「推镜聚焦到某处 + 黄色标注块滑入」的 Remotion 视频输出。 核心是 clone https://github.com/vibe-motion/fisheye-motion 项目并按需改参数渲染。 触发词：鱼眼、fisheye、屏摄、摩尔纹、moire、扫描线、CRT、暗角、vignette、 聚焦推镜、高亮标注动画、screen-photo effect。

Overview

Publishervibe-motion
Repositoryskills
Skill namefisheye-motion
Stars
1.2K
Forks
79
Bundled files
2
Links
Skill sourceRepository
  • 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 vibe-motion on GitHub. Read the source before you install it.

Installation

Install the Fisheye Motion 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.
  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/vibe-motion/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/fisheye-motion .claude/skills/fisheye-motion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fisheye Motion 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 Fisheye Motion 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 Fisheye Motion 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.

Fisheye Motion（鱼眼畸变 + 摩尔纹 + 暗角）

把一张图片（或视频）做成「用手机拍屏幕」的质感：以聚焦点为中心的桶形鱼眼畸变、 跟随画面弯曲的扫描线与固定屏幕扫描线干涉出的摩尔纹、四周暗角； 并可输出「推镜聚焦到目标区域 + 黄色标注块从左滑入」的 Remotion 视频。

工作流程

本 skill 不内置代码，所有实现都在独立仓库里。第一步永远是 clone 项目：

bash
git clone https://github.com/vibe-motion/fisheye-motion.git
cd fisheye-motion

仓库结构：

  • 根目录：Vite + React 交互测试应用（拖图、点击/拖动移动聚焦、导出 PNG）
  • src/lib/FisheyeRenderer.js：与框架无关的 WebGL 渲染器（核心，全部效果的 shader 在这里）
  • src/lib/FisheyeView.jsx：React 组件封装
  • vibe-motion-app/：Remotion 项目，输出聚焦推镜 + 标注滑入的视频

然后根据用户需求走两条路之一。

路线 A：静态效果 / 交互预览（Vite 应用）

bash
npm install
npm run dev
  • 默认加载 public/test.jpg；把用户的图放进 public/ 或直接拖入页面。
  • 点击/拖动画面改变聚焦（畸变中心）；「导出 PNG」保存当前效果帧。
  • 要在自己的 React 项目里复用，直接拷 src/lib/ 两个文件，用法见仓库 README。

路线 B：视频输出（Remotion 项目）

bash
cd vibe-motion-app
pnpm install          # postinstall 自动准备 headless 浏览器
pnpm run dev          # Remotion Studio 预览
  1. 把用户的源图放到 vibe-motion-app/public/ 下。
  2. 改 motion/config.js：
    • imageSrc：public 下的文件名
    • videoWidth / videoHeight：按源图等比取偶数尺寸
    • focusFrom → focusTo：聚焦推镜起止点（0..1 源图坐标，y 向下）
    • rect：标注块位置 { x, y, w, h }（0..1 源图坐标）、颜色、混合模式
    • 时间轴：focusStartSec/focusEndSec（推镜段）、maskStartSec/maskEndSec（标注滑入段）、durationSeconds
  3. 渲染：
bash
# 透明 ProRes 4444 mov（默认）
pnpm run remotion:render

# H.264 mp4
REMOTION_OUTPUT=out/fisheye.mp4 REMOTION_CODEC=h264 REMOTION_PIXEL_FORMAT=yuv420p pnpm run remotion:render
  1. 需要 GIF 预览时用 ffmpeg 转：
bash
ffmpeg -i out/fisheye.mp4 -vf "fps=15,scale=540:-1:flags=lanczos,palettegen" /tmp/p.png
ffmpeg -i out/fisheye.mp4 -i /tmp/p.png -lavfi "fps=15,scale=540:-1:flags=lanczos[x];[x][1:v]paletteuse=dither=bayer:bayer_scale=4" out/fisheye.gif

定位目标区域（rect / focusTo）

用户通常会说「聚焦到 XX 文字/按钮上」。定位方法：

  1. 用多模态视觉读源图，估计目标区域的 0..1 归一化坐标（y 向下）。
  2. focusTo 取该区域中心；rect 框住目标，稍留 padding。
  3. 渲染一帧检查（Studio 里拖时间轴，或 REMOTION_OUTPUT=out/check.png 配合单帧渲染）， 不准就微调坐标重来。畸变会弯曲画面，最终以渲染结果为准。

参数速查

参数默认说明
strength1.6畸变强度，0 = 无畸变，p' = p·(1 + strength·r²) / zoom
zoom2中心缩放（配合聚焦推镜）
moire{ intensity: 0.28, scale: 900, angle: 0 }摩尔纹强度/频率/角度
vignette{ amount: 0.85, radius: 0.72, softness: 0.45 }暗角
rect.blendscreen深色底图白字用 screen；浅色底图深字用 multiply（荧光笔效果）

注意事项

  • Remotion 并行/乱序渲染帧，动画量必须每帧独立计算——已由 motion/timeline.js 保证， 改动画逻辑时保持这一约束，不要引入跨帧状态。
  • 场景用 WebGL shader，headless 渲染需要 --gl angle，渲染脚本已默认设置。
  • 视觉效果非必要不跑自动化验证，渲染后目测（或发关键帧给用户确认）。

效果示例

聚焦推镜到「浙大」二字并滑入黄色标注（assets/fisheye-demo.gif）：

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 Fisheye Motion AI skill do?

制作屏摄风格的鱼眼畸变效果与聚焦动画：桶形鱼眼畸变 + 细扫描线/摩尔纹干涉 + 四周暗角， 可对任意图片/视频做「推镜聚焦到某处 + 黄色标注块滑入」的 Remotion 视频输出。 核心是 clone https://github.com/vibe-motion/fisheye-motion 项目并按需改参数渲染。 触发词：鱼眼、fisheye、屏摄、摩尔纹、moire、扫描线、CRT、暗角、vignette、 聚焦推镜、高亮标注动画、screen-photo effect。

Why use Fisheye Motion on TypingMind?

Because you install it once and use it with any model. Fisheye Motion 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 Fisheye Motion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibe-motion/skills/tree/main/fisheye-motion. 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 Fisheye Motion?

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 Fisheye Motion?

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

Is the Fisheye Motion AI skill free?

It is published on GitHub by vibe-motion. 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.

Related AI Skills

View all
HKUDS logo

Cli Anything Openscreen

HKUDS
OrganizationPopular

Command-line interface for Openscreen — a screen recording editor. A stateful CLI for editing screen recordings with zoom, speed ramps, trim, crop, annotations, and polished exports. Built on the…

4.6K
49.5K
Instructions
View
kepano logo

Obsidian Markdown

kepano
CommunityPopular

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions…

3.5K
48.5K
3 files
View
K-Dense-AI logo

Autoskill

K-Dense-AI
OrganizationPopular

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing…

4.1K
45.4K
13 files
View
github logo

Automate This

github
OrganizationPopular

Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and…

5K
39.1K
Instructions
View

Set up your own AI workspace now

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