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
- Valtz v0.1.0.11 adds FLUX.3 support, local image gen up to 4K on Mac — TgoAI · 2026-10-16
- H3 Character Swap LoRA V1.5 released with open ComfyUI workflow — linoy_tsaban · 2026-10-16
- ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising — VAST-AI · 2026-10-16
- Tokyo's Gemini AI Photo Booth turns visitors into plush toys and dioramas — bradneuberg · 2026-10-16
- AI face-swap of Seinfeld's George Costanza is uncannily convincing — alanskimp · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16