Seedance 2.0 AI Video Generator
Multi-modal reference: up to 9 images, 3 videos, 3 audio tracks in one generation.
Overview
Seedance 2.0 is ByteDance’s multi-modal video model. Unlike single-prompt generators, it accepts up to 9 reference images, 3 reference videos and 3 audio tracks in a single generation, so you can transfer style, motion and sound from existing assets while describing the result in text.
On FAV, Seedance 2.0 auto-routes between text-to-video, image-to-video and reference-to-video based on what you provide. It outputs up to 1080p with flexible aspect ratios (16:9, 9:16, 1:1, 4:3, 21:9) and durations from 1 to 10 seconds.
Billing is by actual duration: credits are reserved at the 15-second maximum when you submit, then the real length is measured and any overpayment is refunded automatically.
⟳ Billed by actual duration — pre-charged at 15s max, refunded after generation.
What you can make
- ✦ Turn a product photo into a rotating showcase clip
- ✦ Transfer the motion of a reference video onto a new subject
- ✦ Generate short social videos from a single text prompt
- ✦ Blend multiple reference images into one coherent scene
Seedance 2.0 FAQ
What is Seedance 2.0?
Seedance 2.0 is a multi-modal AI video model by ByteDance that accepts up to 9 images, 3 videos and 3 audio tracks as references in one generation, supporting text-to-video, image-to-video and reference-to-video up to 1080p.
How much does Seedance 2.0 cost on FAV?
Seedance 2.0 costs 3 cr/s at 480p, 6 cr/s at 720p and 14 cr/s at 1080p. Credits are reserved at the 15-second maximum and the overpayment is refunded based on the actual video length.
What is the difference between Seedance 2.0 and Seedance 2.0 Fast?
Seedance 2.0 Fast offers the same multi-reference capability at lower cost and faster turnaround, but maxes out at 720p (2 cr/s at 480p, 5 cr/s at 720p), while Seedance 2.0 supports up to 1080p.
Related models
Same multi-reference power at lower cost and faster turnaround. Max 720p.
Cinematic output with native audio generation. Fixed durations: 4s, 6s, 8s.
Google's fast variant — same native audio support at lower credit cost.