Search AI Products and News

Qianwen Wanxiang announces the open source of VACE, marking a major technological revolution in the video editing field. This open-sourced Wan2.1-VACE-1.3B supports a resolution of 480P, while Wan2.1-VACE-14B supports both 480P and 720P resolutions. The emergence of VACE brings a one-stop video creation experience to users, allowing them to complete various tasks such as text-to-video generation, image reference generation, local editing, and video extension without frequently switching between different models or tools, greatly improving efficiency.

Scientists at Alibaba Group have introduced VACE, a universal AI model designed to unify a wide range of video generation and editing tasks. At the heart of VACE is an enhanced Diffusion Transformer architecture, innovating with a novel input format called "Video Conditional Unit" (VCU). VCU distills diverse modalities such as text prompts, reference images or video sequences, and spatial masks into a unified representation, and through a specialized mechanism coordinates different inputs to avoid conflicts. Concept decoupling enables fine-grained control.

Still lamenting the high barrier to entry for video production and the complexities of post-editing? Fear not! Alibaba's Tongyi Wan team has launched their latest heavyweight model: the All-in-One video generation and editing model—VACE. One of VACE's most striking capabilities is its powerful conditional video generation function. This means you only need to describe your desired scene in text, and VACE will quickly transform your imagination into reality. It's like having a dream film crew at your command, with astonishing efficiency!