A multi-modal AI video tool for text and image prompts
Seedance 2.0 is a multi-modal AI video generator that turns text prompts and reference media into cinematic videos. It emphasizes controllable motion, style consistency, and fast iteration with reference-driven controls, seamless video extension, and natural language direction across text-to-video and image-to-video workflows.
Multi-modal inputs: text and image prompts for unified workflows
Reference-driven motion and style consistency for predictable results
Production-oriented controls: aspect ratio, resolution, duration, and lens options
Audio-ready pipeline for synchronized sound design
- How to write effective prompts
- AI image styles
No watermark on generated videos
Commercial Use License included
Access to multiple AI video models
Flexible pricing with subscriptions and credits