ByteDance Seedance 2.0
Video generation family with Fast, Mini, and regional tiers across image, reference, and text-driven endpoints.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 12
- Eligible
- 12
- Input schemas imported
- 12 / 12
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Seedance 2.0 spans image-to-video, reference-to-video, and text-to-video endpoints in Fast, Mini, and US tiers. Image input plus a motion prompt drives generation, preserving the source visuals while adding cinematic camera control, realistic physics, and synchronized audio. Native audio covers music, effects, and dialogue. The Fast image endpoint supports multi-shot cuts up to 15 seconds and start-and-end frame control.
Capabilities
- Three video tasks across Fast, Mini, and US tiers
- Director-level camera: dolly zooms, tracking, POV, rack focus
- Realistic physics: weight, collisions, fabric, character motion
- Native music, SFX, and dialogue generation
Best for
- Cinematic camera-move clips
- Physics-grounded animation
- Sound-synced motion content
Use cases
- Start-and-end-frame transitions
- Multi-shot cuts in one generation
- Prompt-directed motion from stills
Endpoints
12 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
bytedance/seedance-2.0/fast/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
bytedance/seedance-2.0/fast/reference-to-video | reference to video | Eligible | 11 fields · requires prompt |
bytedance/seedance-2.0/fast/text-to-video | text to video | Eligible | 8 fields · requires prompt |
bytedance/seedance-2.0/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
bytedance/seedance-2.0/mini/image-to-video | image to video | Eligible | 9 fields · requires prompt, image_url |
bytedance/seedance-2.0/mini/reference-to-video | reference to video | Eligible | 10 fields · requires prompt |
bytedance/seedance-2.0/mini/text-to-video | text to video | Eligible | 7 fields · requires prompt |
bytedance/seedance-2.0/reference-to-video | reference to video | Eligible | 11 fields · requires prompt |
bytedance/seedance-2.0/text-to-video | text to video | Eligible | 8 fields · requires prompt |
bytedance/seedance-2.0/us/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
bytedance/seedance-2.0/us/reference-to-video | reference to video | Eligible | 11 fields · requires prompt |
bytedance/seedance-2.0/us/text-to-video | text to video | Eligible | 8 fields · requires prompt |
Questions
What tiers exist?
Fast, Mini, and US variants across the three video tasks.
How long are Fast generations?
Multi-shot cuts up to 15 seconds on the Fast image endpoint.