DragAnything: Motion Control for Anything using Entity Representation

wu weijia, Zhuang Li, Gu Yuchao, Rui Zhao, Yefei He, David Junhao ZHANG, Mike Shou, Yan Li, tingting gao, Di Zhang

DragAnything: Motion Control for Anything using Entity Representation: 14 upvotes on Hugging Face Daily Papers, #5 of 8 papers on 2024-03-13. Day-by-day upvote history.

We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, DragAnything offers several advantages. Firstly, trajectory-based is more userfriendly for interaction, when acquiring other guidance signals (e.g., masks, depth maps) is labor-intensive. Users only need to draw a line (trajectory) during interaction. Secondly, our entity representation serves as an open-domain embedding capable of representing any object, enabling the control of motion for diverse entities, including background. Lastly, our entity representation allows simultaneous and distinct motion control for multiple objects. Extensive experiments demonstrate that our DragAnything achieves state-of-the-art performance for FVD, FID, and User Study, particularly in terms of object motion control, where our method surpasses the previous methods (e.g., DragNUWA) by 26% in human voting.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.