ByteDance teases Seedance 2.5 with 30-second video and 50 multimodal refs

FellMentKE · x · 2026-07-28

ByteDance’s Dreamina platform is teasing Seedance 2.5, its next AI video model upgrade.

The post says the new version is meant to move beyond short, isolated clips and will support up to 50 multimodal references per generation, up to 30 seconds of continuous video, white-model and green-screen reference control, multilingual creation, and precise local edits. For now, creators can keep using Seedance 2.0 on Dreamina while waiting for the upgrade.

Related event: ByteDance Previews Dreamina Seedance 2.5 with Enhanced Control(3 posts)→

Original post →

More from Multimodal

Multimodal channel →