ECNet: Effective Controllable Text-to-Image Diffusion Models

arXiv:2403.18417v1 Announce Type: new
Abstract: The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reasons, ambiguous condition input and inadequate condition guidance over single denoising loss. To address the challenges, we introduce two innovative solutions. Firstly, we propose a Spatial Guidance Injector (SGI) which enhances conditional detail by encoding text inputs with precise annotation information. This method directly tackles the issue of ambiguous control inputs …

abstract arxiv attention challenges cs.cv denoising diffusion diffusion models guidance however image image diffusion loss precision solutions text text-to-image type