88Z AI, 3 April — Alibaba Tongyi Lab releases the Wan2.7-Video model, supporting full-modal input and instruction-based video editing, with capabilities for subject consistency control, storyboard segmentation, and intelligent plot design.
At a glance
- Supports instruction-based editing for precise modification of video elements, dialogue, and camera angles
- Driven by narrative core for intelligent plotting, supporting multi-subject consistency and professional camera work
The update
Alibaba Tongyi Lab has officially launched the Wan2.7-Video large model for video generation. This model supports full-modal input and introduces an instruction-based video editing feature, allowing users to precisely add, delete, or modify video elements, as well as flexibly adjust dialogue, actions, and camera angles. In terms of content control, Wan2.7-Video maintains feature consistency for up to five subjects, covering advanced applications such as storyboard segmentation, creative replication, and plot continuation. Driven by a core narrative engine, the model enables intelligent plot design, offering over 40 types of facial expressions and professional camera movements, aiming to enhance the controllability and professionalism of video generation.
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.
- 通义实验室Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.