English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent large-scale pre-trained diffusion models have demonstrated a powerfulgenerative ability to produce high-quality videos from detailed textdescriptions. However, exerting control over the motion of objects in videosgenerated by any video diffusion model is a challenging problem. In this paper,we propose a novel zero-shot moving object trajectory control framework,Motion-Zero, to enable a bounding-box-trajectories-controlled text-to-videodiffusion model. To this end, an initial noise prior module is designed toprovide a position-based prior to improve the stability of the appearance ofthe moving object and the accuracy of position. In addition, based on theattention map of the U-net, spatial constraints are directly applied to thedenoising process of diffusion models, which further ensures the positional andspatial consistency of moving objects during the inference. Furthermore,temporal consistency is guaranteed with a proposed shift temporal attentionmechanism. Our method can be flexibly applied to various state-of-the-art videodiffusion models without any training process. Extensive experimentsdemonstrate our proposed method can control the motion trajectories of objectsand generate high-quality videos.

Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation