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

Text-to-video diffusion models have advanced video generation significantly.However, customizing these models to generate videos with tailored motionspresents a substantial challenge. In specific, they encounter hurdles in (a)accurately reproducing motion from a target video, and (b) creating diversevisual variations. For example, straightforward extensions of static imagecustomization methods to video often lead to intricate entanglements ofappearance and motion data. To tackle this, here we present the Video MotionCustomization (VMC) framework, a novel one-shot tuning approach crafted toadapt temporal attention layers within video diffusion models. Our approachintroduces a novel motion distillation objective using residual vectors betweenconsecutive frames as a motion reference. The diffusion process then preserveslow-frequency motion trajectories while mitigating high-frequencymotion-unrelated noise in image space. We validate our method againststate-of-the-art video generative models across diverse real-world motions andcontexts. Our codes, data and the project demo can be found athttps://video-motion-customization.github.io

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models