EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space

Zhixuan Liu, Peter Schaldenbrand, Yijun Li, Long Mai, Aniruddha Mahapatra, Cusuh Ham, Jean Oh, Jui-Hsien Wang

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-12

DOI: 10.1145/3842548 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Zhixuan Liu und 7 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In video diffusion transformers, visual patch tokens maintain explicit correspondence to space and time. We hypothesize that their channel dimension can serve as a semantic control space, which we call Visual Dial Space V + . In this space, additive directions can be broadcast to the token stream to control appearance or motion attributes, enabling slider-style edits such as making a generated person look older or run faster. To verify the hypothesis, we present TokenDial , a framework for learning attribute directions in the proposed V + space. TokenDial keeps the pretrained video generator frozen and optimizes only additive directions. Rather than requiring paired edited videos, TokenDial supervises each direction through its induced effect on generated videos: the edited video should move along the desired attribute while the remaining content stays stable. The learned directions become reusable visual dials that support continuous appearance and motion control, explicit spatiotemporal localization, composition, and reuse across prompts, resolutions, and video lengths. Experiments and human studies show that TokenDial achieves stronger slider controllability and better content preservation than prior video editing and slider-based methods. Project page: https://tokendial.github.io/

Förderung

  • National Science Foundation

Zitieren

APA

Liu, Z., Schaldenbrand, P., Li, Y., Mai, L., Mahapatra, A., Ham, C., Oh, J., & Wang, J. (2026). TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space. ACM Transactions on Graphics, 45(6), 1-12. https://doi.org/10.1145/3842548

Vancouver

Liu Z, Schaldenbrand P, Li Y, Mai L, Mahapatra A, Ham C, et al. TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space. ACM Transactions on Graphics. 2026;45(6):1-12. doi:10.1145/3842548

BibTeX
@article{Liu2026,
  author = {Liu, Zhixuan and Schaldenbrand, Peter and Li, Yijun and Mai, Long and Mahapatra, Aniruddha and Ham, Cusuh and Oh, Jean and Wang, Jui-Hsien},
  title = {TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--12},
  doi = {10.1145/3842548}
}
Kostenlos starten →