About
Seedance is a family of video generation models developed by the Seed team at ByteDance. It spans successive generations — Seedance 1.0 (June 2025), Seedance 2.0 (February 2026), Seedance 2.0 mini and Seedance 2.5 (July 2026). The models generate video from text (text-to-video) and from images (image-to-video), offer native multi-shot storytelling with consistent characters and style, smooth motion and cinematic aesthetics. Newer versions add local editing of scene regions, longer clips and support for many multimodal references. The models are available via API and through ByteDance apps (Doubao/Jimeng/Dreamina) and the Volcano Engine platform.
