ByteDance's Seedance 2.5 Generates 30-Second Videos in One Go: Hands-On

卡尔的AI沃茨 · wechat · 2026-07-31

ByteDance has released Seedance 2.5, its latest AI video generation model. The new version increases single-shot generation time to 30 seconds and supports up to 50 reference materials, enabling coherent short films with complete narrative arcs. Tests show significant improvements in character consistency, realistic facial details (removing the previous waxy look), physics, and multilingual lip-syncing. Additionally, the paired platform introduces a 3D director stage for pre-visualizing camera movements and a partial re-shoot feature, greatly reducing modification costs and lowering production barriers.

Original post →

More from Multimodal

Multimodal channel →