ByteDance launches Seedance 2.5: up to 50 multimodal references and 30-second videos
alifcoder · x · 2026-08-02
ByteDance has officially released Seedance 2.5 on its Dreamina platform. Key upgrades include support for up to 50 multimodal reference assets (images, videos, audio) per generation, and continuous video generation up to 30 seconds, enabling longer and more coherent storytelling. Integrated with Dreamina's editing workflow and multilingual support, it marks a significant step toward production-grade AI video.
Related event: ByteDance Seedance 2.5: 50 refs, 30s video, CapCut integration(33 posts)→
More from Multimodal
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16
- Giant Michael Jackson AI fashion images show the power of extreme proportions — OVolosin82152 · 2026-10-16
- BFL says Flux 3 Klein complaints stem from a Comfy workflow bug, fix underway — desktop4070 · 2026-10-16
- MiniMax H3 + RVC-project combo delivers surprisingly good voice results — ColdComplaint8 · 2026-10-16
- Krea 3 image model impresses with speed: blending three reference images into one — gizakdag · 2026-10-16
- Open-source ebook2audiobook turns any ebook into a free audiobook, 20.4k GitHub stars — thisguyknowsai · 2026-10-16