LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis

arXiv:2311.12342v3 Announce Type: replace
Abstract: Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we propose LoCo, a training-free approach for layout-to-image Synthesis that excels in producing high-quality images aligned with both textual prompts and layout instructions. Specifically, we introduce a Localized Attention Constraint (LAC), leveraging semantic affinity between pixels in self-attention maps to create precise representations …

abstract arxiv control cs.cv diffusion diffusion models exclusive free however image image diffusion images paper prompts quality reliance synthesis text text-to-image textual training type