Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41465-41467
DOI: 10.1609/aaai.v40i48.42308 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tianyu Zhang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Anime hair design is crucial but challenging, as it conveys personality and emotion through stylized geometry and layered structure. In this work, we propose a sketch-guided approach for intuitive control of multimodal diffusion transformers (MMDiT) to generate semantically consistent anime hairstyles. We adopt a wisp-level flowline input integrated with a fine-tuned MMDiT to transfer hairstyles while preserving character identity. We believe that this fine-grained sketch control within the MMDiT framework may offer a promising path for structured anime hair editing.
Zitieren
APA
Zhang, T., Shen, I., & Xie, H. (2026). Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41465-41467. https://doi.org/10.1609/aaai.v40i48.42308
Vancouver
Zhang T, Shen I, Xie H. Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41465-41467. doi:10.1609/aaai.v40i48.42308
BibTeX
@article{Zhang2026,
author = {Zhang, Tianyu and Shen, I-Chao and Xie, Haoran},
title = {Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41465--41467},
doi = {10.1609/aaai.v40i48.42308}
}
EUVIMED