Find any model or tool and jump to its page.
Seedance 2.5 is ByteDance's state-of-the-art AI video model and the successor to Seedance 2.0. Designed for reference-driven work. Built for a higher tier of motion and detail. Write a simple prompt and generate a clip with native sound. Animate a still image into a full scene. Attach up to thirty reference images to hold a character, a product, or a style across shots. Attach reference videos to guide motion and reference audios to drive lip-sync. Generate sound and dialogue alongside the picture. Available in Visual Sandbox alongside Seedance 2.0 and other advanced AI video models, so you can generate, edit, and iterate in a single place. A powerful choice for short film, advertising, music videos, character animation, and concept work.
| Tier | Details | Price |
|---|---|---|
| 480p | Text or image input | $0.13/s |
| 480p | With reference video | $0.54/s |
| 720p | Text or image input | $0.29/s |
| 720p | With reference video | $1.21/s |
Billed per second of output. 480p costs less than 720p, and a reference video raises the rate. Visual Sandbox shows the exact price before you generate.