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)→
More from Multimodal
- Hunting glossy realistic skin in Krea 2 Raw: six LoRAs on test — DragonfruitNo9822 · 2026-10-31
- BEEBS: An AI-Designed Concept Sneaker With Molded EVA Foam Upper — Delahuntagram · 2026-10-31
- AI-Generated Halloween Maid Photos Are Indistinguishable From Real Street Shots — AlchainHust · 2026-10-31
- Star Wars 'dark side' AI images with Vader shadows and a Death Star cloud — egeberkina · 2026-10-31
- MiniMax H3 generates a convincing 90s sitcom scene — Certain_Potato_4509 · 2026-10-31
- Halloween MV 'Skeleton Dogs Don't Need Walkies' stitched from six AI tools — LudovicCreator · 2026-10-31