An AI video-production application that automatically converts novel text into storyboards, characters, scenes, and complete videos. It runs locally via Docker Compose and requires an external AI service API key for inference.
Project overview
It automates the pipeline from novel text parsing to storyboard video production and multi-character voice synthesis within a bilingual interface.
Project type
Image & Vision · Video · Audio & Speech
Use cases
Video Creation
Deployment
Refer to project documentation
License
License pending
Best for
Creators tasked with producing short dramas and comic videos from novel text.
Key capabilities
Automatically parses novels and extracts characters, scenes, and plot information.
Generates consistent character and scene images.
Automatically generates storyboard shots and combines them into video.
Synthesizes voices for multiple roles.
Provides Chinese and English interfaces with one-click switching.
Limitations and risks
Third-party OpenAI-compatible API formats are not yet well supported.
Database versions are currently incompatible across releases, requiring old data to be cleared before upgrading.
The project is in an early testing stage and may contain bugs and incomplete functionality.
Operating-system requirements, GPU requirements, minimum hardware requirements, and named AI service providers and model requirements are not documented.
Getting started
Install Docker Desktop, download the docker-compose.yml file, and run docker compose up -d before opening the documented localhost URL.