ByteDance Launches Seedance 2.5: 30s Generation, 50 Multimodal Reference Assets
ahuja_priyank · x · 2026-08-05
ByteDance's AI video platform Dreamina announced the global launch (including the US) of the Seedance 2.5 model. The new version brings massive upgrades to generation control and narrative consistency:
- Multimodal Reference Control: Supports up to 50 multimodal reference assets (images, videos, audio) per single generation for precise visual execution.
- Long Takes & Consistency: A single generation can deliver up to 30 seconds of continuous footage, significantly reducing awkward cuts and stitching headaches.
- Pro Workflow: Features precise partial editing, 3D white model, and green screen support, stepping directly into a true production workflow.
- Pricing: Seedance 2.5 starts at $0.097/sec, while version 2.0 starts at $0.066/sec, with price matching available.
More from Multimodal
- Dual SAM3 + Seam Mask: A 4K Panoramic 3DGS Reconstruction Workflow — janusch_patas · 2026-08-05
- Suno Music Meets Hailuo Video: A Glimpse at AI Creator Workflows — techhalla · 2026-08-05
- Using Hermes Desktop with ComfyUI: Letting AI Agents Auto-Fix Workflow Errors — Birdinhandandbush · 2026-08-05
- AI Demo Mimics Human Handwriting with Annotations and Streaming Charts — op7418 · 2026-08-05
- Handy ComfyUI Script: Audio Ping Notification for Job Completion — RPGstarDestroyer · 2026-08-05
- Tsinghua's STAMPlus Solves MLLM Segmentation Trilemma with Single-Pass Inference — Tsinghua · 2026-08-05