<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> LocalMiniDrama is an open-source, fully offline tool for generating AI-powered short dramas and comic dramas. It addresses the need for privacy-preserving, end-to-end video creation without relying on cloud services. The tool empowers content creators and developers by offering a flexible, customizable platform for producing AI-driven video content locally.

How It Works

Built on a pure JavaScript stack (Vue3 frontend, Node.js backend with SQLite), LocalMiniDrama orchestrates a complete AI video production pipeline. It integrates with various third-party AI APIs for text, image, and video generation. The workflow spans from story generation and script editing to character, scene, and prop creation, culminating in storyboard generation and final video synthesis, all processed locally to ensure data privacy and user control.

Quick Start & Requirements

• Installation: Recommended for general users is downloading the latest .exe (Standard or Lite) from the Releases page for Windows. Developers can clone the repository and run using Node.js (>= 18) for backend and frontend development.
• Prerequisites: Node.js >= 18 for development. Users must configure API keys for supported AI services (e.g., Aliyun DashScope, Volcengine, Vidu, Kling AI, local Ollama, OpenAI-compatible endpoints).
• Resources: .exe versions offer a quick start. Development requires Node.js setup and API key configuration.
• Documentation: Links to Releases, GitHub/Gitee repos, and detailed guides are available.

Highlighted Details

• End-to-End AI Workflow: Automates story generation, script editing, character/scene/prop creation, storyboard breakdown, image/video segment generation, and final video assembly.
• Broad AI Model Support: Integrates with Aliyun DashScope, Volcengine, Kling AI, Vidu, Google Gemini, NanoBanana, and local Ollama/OpenAI-compatible models for text, image, and video tasks.
• Advanced Storyboard Control: Features "Classic" and "All-around" modes, allowing detailed editing of segment descriptions, image prompts, video parameters (camera, lighting, depth of field), and reference image management.
• Project Management: Supports project export/import, a global asset library for reusing characters, scenes, and props across projects, and customizable aspect ratios.
• Automated Pipeline: Offers one-click generation with automatic retries for errors, real-time progress tracking, and efficient incremental updates.

Maintenance & Community

The project is primarily maintained by its creator, "一个游戏搬砖工." Community interaction is facilitated via WeChat groups (QR code provided, requires author addition) and direct WeChat contact. A roadmap outlines planned features, encouraging community contributions via Issues and Pull Requests.

Licensing & Compatibility

The project is released under the MIT license, which is highly permissive, allowing for commercial use, modification, and distribution without significant restrictions. This license is compatible with closed-source applications.

Limitations & Caveats

The provided .exe installers are Windows-specific. The tool relies on users obtaining and configuring their own API keys for various AI services. While robust, the project appears to have a single primary maintainer, indicating a potential bus factor. Ongoing development is evident through frequent updates and a public roadmap.