ByteDance's Dreamina Launches Seedance 2.5: Native 30s Video Generation
HeyAmit_ · x · 2026-08-09
ByteDance's AI platform Dreamina has officially launched Seedance 2.5 in the US, focusing on cinematic storytelling and precision control.
Key Features:
- Long Video Generation: Native generation up to 30 seconds per take, with a long video mode extending up to 3 minutes while maintaining consistency.
- Precision Editing: A new interactive editing experience supporting frame-level reshaping and 1-second timestamp control.
- Multimodal References: Supports up to 50 multimodal references, including 3D white models and green-screen footage.
- Workflow Integration: Released plugins for Maya and Blender to integrate AI generation directly into film-grade production pipelines.
- Visual Upgrades: More true-to-life lighting and shadows with richer motion details.
More from Multimodal
- xllm generates an image in 0.4 seconds — warycat · 2026-08-24
- Wan 3.0 Video Generation Demo: Single Prompt, First Attempt — OdinLovis · 2026-08-24
- Wan 3.0 launches on fal with native 30-second video generation — aziz4ai · 2026-08-24
- Animation workflow combining LTX2.3 FLFA2V and Suno Audio — JustRuss79 · 2026-08-24
- Minimax H3 T2VA supports 15+ characters simultaneously on screen — beatlepol · 2026-08-24
- How to replace an image element with Flux Kontext or Qwen Image Edit? — Wemos_D1 · 2026-08-24