- Text-to-video generation with natural motion and physics-aware rendering
- Image-to-video animation and motion synthesis
- Multi-modal input: combine images, short videos, audio, and text
- Reference-anything: use uploaded content as motion/style references
- Video extension and multi-shot storytelling
- Built-in audio generation: effects and background music
- High consistency for faces, clothing, text, and scene elements
- API access and tiered credit-based pricing
- Export in multiple aspect ratios and up to 2K/4K (depending on plan)