huangserva GitHub avatar

editorial-card-video

huangserva

A one-click video generation skill that creates 20-24 second magazine-style information card videos from a content specification JSON file.

Stars

51

7-day growth

No data

Forks

7

Open issues

0

License

No data

Last updated

2026-07-04

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It reduces complex video production to editing a single JSON file, with built-in quality control checks and multiple scene blueprints, making high-quality card videos accessible without manual editing.

Who it is for

  • Content creators who need rapid video production
  • Video editors looking for template-driven workflows
  • Product teams wanting to automate social media videos
  • AI tool developers evaluating skill-based generation pipelines

Use cases

  • Generating promotional social media shorts from product specs
  • Creating consistent informational card videos for online courses
  • Rapid prototyping of magazine-style video ads
  • Automating video generation for recurring content updates

Strengths

  • Fully parameterized with 13 components and 6 scene blueprints
  • Includes a comprehensive QC checklist (8 scripts) to ensure output quality
  • Supports three card types (single video card, live triple card, dark full‑bleed card)
  • Uses proven design language from an existing social card skill

Considerations

  • Requires Node.js, ffmpeg, Python 3 with Pillow/numpy, and HyperFrames
  • Output style is limited to a specific paper‑textured editorial card aesthetic
  • Content must follow the provided content‑spec guide and media rules

README quick start

安装

Description

editorial-card-video 是一个"内容表 → 成片"的一键视频生成 skill。只需填一份 content-spec(标题、要点、配图、BGM),即可自动生成一支 20-24 秒的纸感编辑风信息卡视频:米白纸底、Swiss 杂志排版、右侧活卡——卡内视频实时播放、层叠入场、锚定微漂,宛如会呼吸的杂志页。

Related repositories

Similar projects matched by category, topics, and programming language.

ddosi
Featured
ddosi GitHub avatar

PacketLens

PacketLens is a pure front-end, offline pcap analysis tool that runs entirely in the browser, supporting deep protocol decoding, HTTPS decryption, and million-packet instant loading without any backend.

HTML
19
ViffyGwaanl
Featured
ViffyGwaanl GitHub avatar

kimi-k3-learn

An interactive learning system that turns the 47-page Kimi K3 technical report into a single offline HTML file with running algorithms, 3D visualizations, spaced repetition quizzes, and a smart highlighting QA tool.

AI & Machine Learning
15
iamtechartist
Featured
iamtechartist GitHub avatar

human-cell-visualizer

An interactive 3D visualization of three human cell types using Three.js, WebGL particles, and custom GLSL shaders, allowing users to rotate, zoom, morph, and explore annotated structures.

Design & Creative
13