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
- Tripo's first World-Building Hackathon lands in SF with World Labs, Runway — mhdfaran · 2026-10-16
- Pollo AI launches Recast video restyling, 60% off for launch — SimplyAnnisa · 2026-10-16
- Kling 4.0 boosts text-to-video with character consistency and lip sync — CurieuxExplorer · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16
- Huawei's SUPRA-Tex turns one image into relightable 3D materials with WYSIWYG fidelity — Chen Yang · 2026-10-16
- Giant Michael Jackson AI fashion images show the power of extreme proportions — OVolosin82152 · 2026-10-16