ByteDance's Seedance 2.5 lands on Scenario with 50 multimodal references support

aziz4ai · x · 2026-08-07

ByteDance's video generation model Seedance 2.5 is now available on the AI creation platform Scenario.

The model can generate up to 30 seconds of video in a single generation and accepts up to 50 multimodal references. It handles complex prompts including turntables, lookbooks, camera motion, and audio, while maintaining consistent characters from the first frame to the last.

Original post →

More from Multimodal

Multimodal channel →