Tianyi Wei, Yifan Zhou 0001, Dongdong Chen, Xingang Pan. FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 16745-16754, IEEE, 2025. [doi]
Abstract is missing.