1. [Publications](/index.php/publications)
2. Identity-Motion Trade-offs in Text-to-Video Generation
 
 # Identity-Motion Trade-offs in Text-to-Video Generation

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 Text-to-video diffusion models have shown remarkable progress in generating coherent video clips from textual descriptions. However, the interplay between motion, structure, and identity representations in these models remains under-explored. Here, we investigate how self-attention query (Q) features simultaneously govern motion, structure, and identity and examine the challenges arising when these representations interact. Our analysis reveals that Q affects not only layout, but that during denoising Q also has a strong effect on subject identity, making it hard to transfer motion without the side-effect of transferring identity. Understanding this dual role enabled us to control query feature injection (Q-injection) and demonstrate two applications: (1) a zero-shot motion transfer method — implemented with VideoCrafter2 and WAN 2.1 — that is 10x more efficient than existing approaches, and (2) a training-free technique for consistent multi-shot video generation, where characters maintain identity across multiple video shots while Q-injection enhances motion fidelity.



 ## Authors



[Yuval Atzmon](/index.php/person/yuval-atzmon)

Rinon Gal

[Yoad Tewel](/index.php/person/yoad-tewel)

[Yoni Kasten](/index.php/person/yoni-kasten)

[Gal Chechik](/index.php/person/gal-chechik)

 

 

 ## Publication Date



Friday, July 25, 2025

 

 ## Published in



[BMVC 2025](https://bmvc2025.bmva.org/proceedings/159/)

 

 ## Research Area



[Algorithms and Numerical Methods](/index.php/research-area/algorithms)

[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/index.php/research-area/computer-graphics)

[Computer Vision](/index.php/research-area/computer-vision)

[Generative AI](/index.php/research-area/generative-ai)

 

 

 ## External Links



[Project page](https://research.nvidia.com/labs/par/MotionByQueries/)