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.

DragAnything 利用实体表示来实现对可控视频生成中的任何对象的运动控制。与现有的运动控制方法相比，DragAnything 具有几个优势：轨迹为基础的方法更易于用户交互，不需要获取其他指导信号（例如，遮罩、深度图）的工作字眼；用户只需在交互过程中绘制一条线（轨迹）。其次，我们的实体表示作为一个开放域的嵌入，能够表示任何对象，实现对各种实体（包括背景）的运动控制。最后，我们的实体表示允许同时对多个对象进行不同的运动控制。大量实验证明，DragAnything 在 FVD、FID 和用户研究方面实现了最先进的性能，尤其在对象运动控制方面，我们的方法在人类投票中比以前的方法（例如 DragNUWA）提高了 26%。