88Z AI, 7 August — Alibaba's new generation video generation model Wan3.0 has launched public beta on the Duiyou platform, supporting 30-second video generation and multimodal inputs, with significantly improved character consistency and editing capabilities.
At a glance
- Wan3.0 supports 30-second video generation and multimodal reference inputs
- Enhanced consistency in characters, props, and audio along with improved video editing capabilities
The update
Alibaba's new generation video generation model Wan3.0 has officially launched its public beta on the Duiyou platform, simultaneously introducing the Duiyou Agent and video generation module. The model supports generating single video segments up to 30 seconds long, featuring intelligent duration recommendations and video extension capabilities. It accepts multimodal references including text, images, and videos, enabling video generation from various sources. Furthermore, the model delivers diverse portrait renderings while maintaining high consistency in characters, props, and audio, significantly enhancing video editing capabilities for a more precise and efficient creative experience.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 堆友Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.