EUVIMEDEUVIMED entdecken
Crossref

DiffMagicFace: Identity consistent facial editing of real videos

Huanghao Yin, Shenkun Xu, Kanle Shi, Jun-Hai Yong, Bin Wang

iFuture · 2026

DOI: 10.26599/if.2026.9710003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift iFuture, 2026. Verfasst von Huanghao Yin und 4 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-conditioned image editing has greatly benefited from the advancements in image diffusion models. However, extending these techniques to facial video editing introduces challenges in preserving facial identity throughout the source video and ensuring consistency of the edited subject across frames. In this paper, we introduce DiffMagicFace, a unique video editing framework that integrates two fine-tuned models for text and image control. These models operate concurrently during inference to produce video frames that maintain identity features while seamlessly aligning with the editing semantics. To ensure the consistency of the edited videos, we develop a dataset comprising images showcasing various facial perspectives for each edited subject. The creation of a dataset is achieved through rendering techniques and the subsequent application of optimization algorithms. Remarkably, our approach does not depend on video datasets but still delivers high-quality results in both consistency and content. The excellent effect holds even for complex tasks like talking head videos and distinguishing closely related categories. The videos edited using our framework exhibit parity with videos that are made using traditional rendering software. Through comparative analysis with current state-of-the-art methods, our framework demonstrates superior performance in both visual appeal and quantitative metrics.

Zitieren

APA

Yin, H., Xu, S., Shi, K., Yong, J., & Wang, B. (2026). DiffMagicFace: Identity consistent facial editing of real videos. iFuture. https://doi.org/10.26599/if.2026.9710003

Vancouver

Yin H, Xu S, Shi K, Yong J, Wang B. DiffMagicFace: Identity consistent facial editing of real videos. iFuture. 2026. doi:10.26599/if.2026.9710003

BibTeX
@article{Yin2026,
  author = {Yin, Huanghao and Xu, Shenkun and Shi, Kanle and Yong, Jun-Hai and Wang, Bin},
  title = {DiffMagicFace: Identity consistent facial editing of real videos},
  journal = {iFuture},
  year = {2026},
  doi = {10.26599/if.2026.9710003}
}
Kostenlos starten →