ByteDance Seedance 2.5 Rolls Out Native 30-Second AI Video via Dreamina and CapCut

ByteDance

Video official + media 4 src. ~1 min

ByteDance launched Seedance 2.5 to consumer platforms (Dreamina internationally, Jimeng in China) in early July, with CapCut integration rolling out in mid-July 2026 and the BytePlus API officially launching July 16. The model generates continuous 30-second video clips in a single pass without stitching, accepts up to 50 simultaneous multimodal reference inputs, supports 4K output, and includes per-region local editing of generated frames without regenerating the full clip.

Why it matters

First mainstream AI video model to deliver seamless 30-second single-pass generation, raising the duration baseline for the category and distributing the capability through CapCut's 400M+ monthly active users.

Importance: 3/5

Consumer rollout of native 30-second single-pass AI video via CapCut's massive distribution; first to break the 20-second stitched-clip barrier at consumer scale

Sources