Video
Seedance 2.0
ByteDance's flagship multimodal video model — unified audio-video generation with omni-reference director controls.
About this model
Seedance 2.0 is ByteDance's next-generation video model with a unified audio-video architecture: dialogue, ambient sound, and music are generated in the same pass as the visuals, producing natural lip sync and physics-aware sound effects. Its omni-reference mode accepts up to 9 images, 3 video clips, and 3 audio files — referenced in prompts with @Image1, @Video1, @Audio1 syntax — so you can combine character look, motion style, and rhythm in one render. On HiArt, Seedance 2.0 is the choice for short-form ads, music-synced content, and multi-asset campaigns that start on the image canvas.
Best for
- Native audio-video co-generation with lip sync in 8+ languages
- Omni-reference: up to 9 images, 3 videos, and 3 audio clips per render
- Text-to-video, first/last frame, and omni-reference modes
- 4–15 second clips at 480p, 720p, or 1080p
- Adaptive aspect ratio and improved motion physics
- Director-level control over camera, rhythm, and subject motion
Common workflows
- Short-form ads with synced voiceover and sound design
- Music-synced social clips using an audio reference track
- Character videos that must match still-frame references from image models
- Product showcase videos combining pack shots and motion references
- Multi-shot narrative sequences with consistent subject identity
How to use on HiArt
- 01Add a video node and select Seedance 2.0 on the HiArt canvas.
- 02Pick a mode: text-to-video, first/last frame, or omni-reference.
- 03Attach reference media and cite them in the prompt (@Image1 performs motion from @Video1).
- 04Enable audio generation, set duration (4–15 s) and resolution, then generate and iterate.
Capabilities
- Provider
- ByteDance Seed
- Modes
- Text-to-video, first/last frame, omni-reference
- Duration
- 4–15 seconds
- Resolution
- 480p, 720p, 1080p
- Omni-reference limits
- 9 images, 3 videos (≤15 s total), 3 audio clips (≤15 s total)
- Audio
- Native generation with lip sync
Learn more
- Seedance 2.0 API documentation
Technical readme covering modes, reference syntax, and prompting tips.
- Seedance 2.0 release overview
Developer-focused breakdown of omni-reference and audio-video co-generation.
- Seedance 2.0 vs 1.5 Pro
Comparison of architecture, duration, and reference capabilities.
FAQ
- What is omni-reference mode?
- Omni-reference lets you attach multiple images, videos, and audio files as creative inputs — not just a start frame. Reference each asset in your prompt to combine appearance, motion, and rhythm in one generation.
- Should I use Seedance 2.0 or 2.0 Fast?
- Use Seedance 2.0 Fast for motion previews and rapid iteration at 480p/720p. Switch to full Seedance 2.0 when you need 1080p output or the highest motion and audio quality.
Related models
Try on the canvas
Sign up free, open a project, and set model preferences before you generate.