Why choose it
- Animate, first/last, and references
- Four-to-fifteen-second shots
- Image modes up to 1080p
Original model creator
ByteDance
Seedance 2.0
A flexible text-and-image model with first/last-frame direction, up to nine references, broad formats, and optional audio.
Loading Seedance 2.0 sample
Independent testSourced output
Independent test · Results vary by prompt and settings
See the model move.
Direct answer
When should you use Seedance 2.0?
Seedance 2.0 fits productions that need more control over source material, format, and shot length. Animate one image, direct a transition between two frames, or use up to nine references for consistency across social, feed, and widescreen placements.
Best for
Multi-format ad concepts, longer social shots, and creative teams testing several delivery formats.
Technical readout
The supported shot envelope.
- Duration
- 4–15 seconds
- Resolution
- 480p–1080p depending on input mode
- Aspect ratio
- Landscape, portrait, and square formats
- Audio
- Optional generated audio
What to consider
- Higher settings materially change generation cost
- Video Lab uses fixed timing for predictable direction and pricing
Prompt direction
How to prompt Seedance 2.0
Write one continuous action with a clear beginning and end, then select the intended channel format before generating.
Start a Seedance 2.0 promptQuestions, answered
Seedance 2.0 FAQ
What is Seedance 2.0 best for?
Seedance 2.0 is useful when you need longer clips or want to adapt one concept across several aspect ratios and resolutions.
How long can a Seedance 2.0 clip be?
Video Lab exposes supported fixed durations from 4 to 15 seconds.
Can Seedance 2.0 use several reference images?
Yes. Video Lab supports up to nine reference images, as well as single-image animation and first-to-last-frame direction.
Change the lens
Compare Seedance 2.0 with another model.
Official sampleByteDanceOriginal model creatorSeedance 2.5
A next-generation text-and-image video model with native audio, 30-second shots, first/last frames, and deep reference control.See model
Official sample
GoogleOriginal model creatorVeo 3.1
A premium text-and-image video model for cinematic shots, guided frames, references, optional audio, and up to 4K output.See model
Official sample
KuaishouOriginal model creatorKling 3 Pro
A controllable text-and-image model for expressive movement, first/last frames, subject references, and optional audio.See modelByteDance lens selected
Direct your first Seedance 2.0 shot.
Write the prompt, choose supported controls, and see the exact credit quote before you generate.
Open Seedance 2.0 in Video Lab