An AI coding-assistant skill that turns a sentence into a Live Photo-style animated cover with charts, emoji and timelines, built on Remotion.
gnipbao/story-to-handdrawn-video
Agent skill that turns Chinese story text or ordered images into a silent 3:4 hand-drawn diary-comic video rendered with Remotion.
- Stars
- 2,383
- Forks
- 330
- Open issues
- 2
- Last commit
- 2 months ago
What is it?
story-to-handdrawn-video turns Chinese story copy or an ordered set of images into a vertical hand-drawn animation. An AI agent plans the storyboard, generates illustrated master pages with handwritten Chinese captions through its image tool, and a local pipeline splits them into layers. Remotion then plays the result as a silent H.264 MP4 at 720×960 or 1080×1440, ready for voiceover or music in post-production.
Two animation modes are supported. Layered mode reveals the text, a grayscale version of the art derived from the color illustration, and then the color art, from left to right. Page-flip mode keeps each full page intact and curls it from the bottom-right corner to reveal the next. The project includes a catalog of 297 style recipes and 30 color palettes, a curated default menu of 30 styles, and a workflow for analyzing a reference image and saving its style for reuse.
The project ships as a Remotion renderer plus an installable Agent Skill that works with agents such as Codex, Claude Code and Kimi Code. It requires Node.js 20+, Python 3.10+, FFmpeg, and an image-generation tool available to the agent for creating new artwork.
Key features
- 01Turns Chinese story text or ordered images into a silent 3:4 vertical MP4.
- 02Generates illustrations with exact handwritten Chinese captions in one pass.
- 03Layered mode reveals text, grayscale art and color art in sequence.
- 04Page-flip mode curls through complete original pages from the bottom-right corner.
- 05Includes 297 style recipes and 30 color palettes, plus a browsable offline catalog.
- 06Analyzes reference images and saves custom styles for later reuse.
Use cases
- Making hand-drawn diary-style or picture-book videos from a short story.
- Animating a set of already-drawn illustrated pages in sequence.
- Previewing and comparing art styles before committing to a full render.
- Producing silent video drafts that will receive voiceover or music later.
Quick start
- 1
Clone the repository
git clone https://github.com/gnipbao/story-to-handdrawn-video.git - 2
Enter the project folder
cd story-to-handdrawn-video - 3
Install the renderer dependencies
npm ci - 4
Copy the Skill into your Codex skills folder
cp -R skill-package/story-to-handdrawn-video ~/.codex/skills/
Things to know
- Creating new artwork requires an image-generation tool available to your Agent.
- Requires Node.js 20+, Python 3.10+, FFmpeg and a compatible browser.
- Exported videos are silent, so voiceover and music must be added in post-production.
In collections
Topics
FAQ
- What is story-to-handdrawn-video?
- Agent skill that turns Chinese story text or ordered images into a silent 3:4 hand-drawn diary-comic video rendered with Remotion. story-to-handdrawn-video turns Chinese story copy or an ordered set of images into a vertical hand-drawn animation. An AI agent plans the storyboard, generates illustrated master pages with handwritten Chinese captions through its image tool, and a local pipeline splits them into layers. Remotion then plays the result as a silent H.264 MP4 at 720×960 or 1080×1440, ready for voiceover or music in post-production.
- Is story-to-handdrawn-video free to use? What license does it have?
- story-to-handdrawn-video is open source under the MIT license. Check the license terms before using it in commercial products.
- Is story-to-handdrawn-video still maintained?
- Updated within 6 months. The last commit to story-to-handdrawn-video was on Sep 22, 2026.
- What can I use story-to-handdrawn-video for?
- Making hand-drawn diary-style or picture-book videos from a short story. Animating a set of already-drawn illustrated pages in sequence. Previewing and comparing art styles before committing to a full render. Producing silent video drafts that will receive voiceover or music later.
- How do I install story-to-handdrawn-video?
- Clone the repository: git clone https://github.com/gnipbao/story-to-handdrawn-video.git Enter the project folder: cd story-to-handdrawn-video Install the renderer dependencies: npm ci Copy the Skill into your Codex skills folder: cp -R skill-package/story-to-handdrawn-video ~/.codex/skills/
- Where can I get story-to-handdrawn-video?
- The source code and installation instructions are on GitHub: https://github.com/gnipbao/story-to-handdrawn-video
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Claude Code skill that guides Claude Opus 5.5 to plan, build, render and QA short videos written as HTML, Canvas, SVG, Three.js, GSAP or Remotion code.
Agentic video generation framework that turns a story idea, screenplay, or novel into a multi-shot video by coordinating script, storyboard, character, and video generation agents.
Open-source AI film and short-drama creation workspace with an infinite canvas for storyboarding, multimodal generation and asset management.
A local node-based canvas for AI image, video and storyboard creation, with an in-canvas agent, a 3D director studio and pluggable generation providers.
Desktop AI art engine that combines a node graph, specialized editors and a 3D director stage for generating short-video, game and advertising assets, with local-first model access.