01
Multi-modal inputs
Unified multi-modal inputs—text, images, and audio/video references
Try Seedance 2.0AI Video Model
Seedance 2.0 — AI video generator
Seedance 2.0 focuses on multi-modal input and synchronized audio—guide characters, style, and choreography with rich references.
Visual inspiration
Find your next creative direction
Explore visual inspiration for stories, product scenes, and your next video brief.
Capabilities
Create with Seedance 2.0
More inputs. More control. More story.
From idea to video
How it works
Step 1 · Gather your inputs
Bring text, references, and any audio/video cues that define the story.
Step 2 · Generate with Seedance
Create audio-visual clips that respect identity, style, and pacing.
Step 3 · Tell the multi-shot story
Iterate coverage until the narrative feels coherent from beat to beat.
Best for
Real scenarios you can ship today.
Multi-shot narrative clips with consistent identity
Audio-forward ads and explainers
Reference-heavy productions with controlled style
Frequently asked
Multi-modal storytelling—when you want text, references, and audio working together in one generation.
AI models
Explore other models
Different models shine at different jobs. Browse the full lineup or jump to a close alternative.
Ship faster
Work with Seedance 2.0 like a production copilot.
Move from first draft to final delivery in one flow. Generate, verify, refine, and publish with confidence.