Seedance 2.5 Released: Supports 50 Reference Inputs and 30-Second Videos
ZabihullahAtal · x · 2026-08-07
Seedance 2.5 introduces four major upgrades to its video generation capabilities:
- Multimodal References: Supports up to 50 reference inputs for improved character and scene consistency.
- Longer Video Output: Generates videos up to 30 seconds long, with better support for multi-shot scenes, multiple characters, and continuous storytelling.
- Video Editing Workflow: Allows users to modify, restructure, and transform video styles.
- Cinema-grade Quality: Outputs high-definition, native-quality imagery directly.
Practical Demo:
A test video featuring a huntress riding a giant wolf demonstrated consistent characters, smooth rider-and-wolf interaction, dynamic camera movements, and stable motion across complex terrains.
Commercial Use Cases:
The model is tailored for e-commerce product videos, UGC ads, and multilingual content creation. It is currently available on the Lovart platform, with annual subscribers eligible for free generation credits.
More from Multimodal
- Pollo AI launches Recast video restyling, 60% off for launch — SimplyAnnisa · 2026-10-16
- Tripo hosts first world-building hackathon in SF with World Labs and Runway talks — mhdfaran · 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