ByteDance's Dreamina Launches Seedance 2.5: Supports 30-Second Video Generation
SucceededMind · x · 2026-08-02
ByteDance's AI creative platform Dreamina has launched the new Seedance 2.5 video generation model. This upgrade significantly enhances the physics and motion logic in complex visual generation.
The new system supports up to 50 multimodal reference assets (including images, videos, and audio) in a single generation and can produce continuous videos up to 30 seconds long. Combined with the platform's built-in editing workflow and multilingual support, the tool aims to further bridge the gap for AI video in real production environments.
Related event: ByteDance Seedance 2.5: 50 refs, 30s video, CapCut integration(33 posts)→
More from Multimodal
- Cinematic 3D fantasy character prompt template with salvaged-robot armor — azed_ai · 2026-10-16
- MOSS-Image INT8 quantization lands for ComfyUI, near-lossless per author — East_Shoe8814 · 2026-10-16
- 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