AI RESEARCH
Training-Free Layout-to-Image Generation with Marginal Attention Constraints
arXiv CS.CV
•
ArXi:2411.10495v3 Announce Type: replace Recently, many text-to-image diffusion models have excelled at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works have developed layout-to-image (L2I) approaches that incorporate layout instructions into text-to-image models. However, existing L2I methods typically require fine-tuning of pre-trained parameters or