Rethinking attention modules of SDXL in a flow perspective

DOI10.3934/MFC.2025015MaRDI QIDQ6876427zbMATH OpenFDO

Authors Zeyuan Gao, Juxiang Zhou, Jianhou Gan, Jiatian Mei

Publication date 13 January 2026

Published in Mathematical Foundations of Computing (Search for Journal in Brave)

zbMATH Keywords

diffusion modelsimage generationflow matchingtext-to-imagetraining free methods

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Knowledge representation (68T30) Machine vision and scene understanding (68T45)

This page was built for publication: Rethinking attention modules of SDXL in a flow perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6876427)