openstory-so/openstory
Open-source AI-powered video sequence platform built with TanStack Start
What it solves
OpenStory automates the process of turning written scripts into styled video productions. It eliminates the manual effort of prompt engineering and asset creation by coordinating AI-generated images, motion video, and audio while maintaining visual consistency across different scenes.
How it works
The platform uses a multi-step AI pipeline:
- Script Analysis: It analyzes scripts to create scene breakdowns, including camera angles, mood, and continuity tracking.
- Asset Generation: It leverages Fal.ai for generating images, turning those images into motion video clips, and creating audio.
- Consistency Management: It ensures that characters, locations, color palettes, and lighting remain consistent across the entire production.
- Deployment: The system is built on Cloudflare Workers, using D1 for the database and R2 for storage, allowing it to run at the edge.
Who it’s for
It is designed for creative teams and storytellers who want to produce AI-driven video content from scripts without needing to manually manage complex AI prompts or asset continuity.
Highlights
- Automatic Scene Breakdown: Converts scripts into actionable production details like camera angles and mood.
- Visual Continuity: Automatically carries characters and styles across scenes.
- Image-to-Video: Converts still AI-generated frames into motion clips.
- Social Integration: Optional ability to publish finished renders directly to platforms like TikTok, Instagram, and YouTube.
- Edge-Native Stack: Fully deployed on Cloudflare Workers for global performance.
Related
- Project
- Project
- Project
- Project
- Project