Compositional Text-to-Image Synthesis With Training-Free Layout-Guided Diffusion

Xiaoling Gu, Lingwei Luo, Shengqi Wu, Zizhao Wu, Zhenzhong Kuang, Zhou Yu 0001. Compositional Text-to-Image Synthesis With Training-Free Layout-Guided Diffusion. IEEE Transactions on Multimedia, 28:4169-4180, 2026. [doi]

Abstract

Abstract is missing.