Dual Production Engines
Choose between customized interactive creation and automated bulk video generation.
Creative Mode
Auto-generates a complete plan: brief, story, storyboard, voiceover, plates, and BGM from one sentence. Keep full creative control with inline manual editing.
- Interactive storyboard preview with audio sync
- 34 built-in art styles across 9 categories
- Multiple TTS voice options with real-time preview
- Supports 16:9 cinematic, 9:16 portrait, and 1:1 square layouts
- Export resolutions up to 1080p Full HD
Batch Mode
Designed for bulk production of short videos. Input topics, and the AI automatically writes multiple scripts, retrieves stock footage, and generates high-converting clips.
- Topic-to-video batch generation engine
- Customizable clip duration & transition pacing
- Subtitle overlay with custom fonts, colors, and positioning
- Royalty-free HD footages from Pexels & Pixabay
- Generate multiple variants at once to select the best
Mode Comparison
Creative Mode
- •Ideal for professionals who need fine-grained control
- •Supports manual editing at every production stage
- •Interactive storyboard preview with real-time adjustments
- •Access to all 34 art styles
- •Highest output quality, suitable for cinematic productions
Batch Mode
- •Ideal for content creators who need high-volume output
- •Generate multiple video variants with one click
- •Auto-matched royalty-free HD stock footage
- •Highly customizable subtitle styles
- •Bulk export for maximum efficiency
Technical Specifications
Supported AI Models
OpenDirector uses OpenAI-compatible API format, supporting multiple LLM providers. Choose based on your needs and budget.
Technology Stack
OpenDirector uses a modern full-stack architecture: LangGraph orchestrates the multi-agent pipeline, Next.js powers the responsive web interface, and FFCreator with FFmpeg handles video rendering. The platform supports one-click Docker deployment with built-in MySQL for data storage, Redis for caching and queues, and MinIO for object storage. All AI agents communicate through OpenAI-compatible API interfaces, supporting OpenAI, Anthropic, DeepSeek, Google Gemini, and Ollama local models.