AnimateAnything: Consistent and Controllable Animation for Video Generation
This addresses the challenge of generating stable and controllable videos for applications in media and AI, representing a strong incremental improvement over existing methods.
The paper tackles the problem of controllable video generation by introducing AnimateAnything, a unified approach that enables precise and consistent video manipulation using conditions like camera trajectories and text prompts, resulting in state-of-the-art performance.
We present a unified controllable video generation approach AnimateAnything that facilitates precise and consistent video manipulation across various conditions, including camera trajectories, text prompts, and user motion annotations. Specifically, we carefully design a multi-scale control feature fusion network to construct a common motion representation for different conditions. It explicitly converts all control information into frame-by-frame optical flows. Then we incorporate the optical flows as motion priors to guide final video generation. In addition, to reduce the flickering issues caused by large-scale motion, we propose a frequency-based stabilization module. It can enhance temporal coherence by ensuring the video's frequency domain consistency. Experiments demonstrate that our method outperforms the state-of-the-art approaches. For more details and videos, please refer to the webpage: https://yu-shaonian.github.io/Animate_Anything/.