HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models

Published in the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)

If the embedded viewer does not load in your browser, open the PDF directly: Open PDF

Cite: Yeqi He, Liang Li, Zhiwen Yang, Xichun Sheng, Zhidong Zhao, and Chenggang Yan. HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026: 3914-3923.
Publisher | BibTeX