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
- MiniMax H3 Beats Seedance 2.0 in Hands-On Video Generation Test — socialwithaayan · 2026-07-31
- Grok Imagine Video Generation Test: Incredibly Realistic Results — XFreeze · 2026-07-31
- Seedance 2.0 Workflow: Generating Dynamic Band Videos Using Reference Images and Stills — techhalla · 2026-07-31
- Unlocking AI Video Workflows in Magnific with 1 Image and 3 Prompts — techhalla · 2026-07-31
- Testing Invideo Agent One: Create Anime Shorts from Scratch via Chat — LudovicCreator · 2026-07-31
- Claude Acts as Motion Designer via Higgsfield MCP, Accessing 30+ Video Models — dr_cintas · 2026-07-31