by ByteDance
ByteDance's video generation model with high motion quality and dance/movement specialization.
Seedance 2.0 by ByteDance is a next-generation video generation model specializing in human motion, dance, and audio-visual synchronization. Released in February 2026, it produces 2K resolution output with unprecedented naturalness in human movement modeling, phoneme-level lip-sync in 8+ languages, and multi-modal input support.
A professional dancer performing contemporary choreography
in an abandoned warehouse, dramatic side lighting casting
long shadows, dust particles in the air, cinematic camera
slowly circling, 9:16 vertical format
Seedance excels at detailed human motion — be specific:
A street dancer hitting a freeze pose, then flowing into
a windmill, graffiti wall backdrop, boom box nearby,
golden hour sunlight, dynamic low-angle camera
For dance content, provide audio files for rhythm-matched generation. V2 supports up to 3 audio files.
| Parameter | Description |
|---|---|
| duration | 4-15 seconds |
| aspect_ratio | 16:9, 9:16, 1:1 |
| fps | Frame rate (default 24) |
| resolution | 480P, 720P, 1080P, 2K |
| audio | Audio for rhythm synchronization (up to 3 files in v2) |
| style | Dance style template: street dance, K-pop, ballet, modern |
Quick tips from the community about what works with Seedance 2.0 right now.
Sign in to share a tip.
No tips yet. Add a tip for this model.