Wan Move is an open-source research codebase for motion-controllable video generation that focuses on enabling fine-grained control of motion within generative video models. It is designed to guide the temporal evolution of visual content by leveraging latent trajectory guidance, allowing users to manipulate how objects move over time without modifying the underlying generative architecture. By representing motion information as dense point trajectories and integrating them into the latent space of an image-to-video model, the project produces videos with more precise and controllable motion behavior than many existing methods. Wan-Move is particularly notable for eliminating the need for additional motion encoders, instead directly infusing motion cues into spatiotemporal features, which simplifies both training and inference.
Features
- Motion controllable video synthesis via latent trajectory guidance
- Dense point trajectory representation for fine-grained motion control
- Seamless integration into existing image-to-video models
- Elimination of auxiliary motion encoders
- Scripts and configs for reproducible research
- Scalable framework suitable for research workflows