Universal Guidance for Diffusion Models
University of Maryland, College Park · Department of Computer Science, University of Maryland, College Park · Carnegie Mellon University · Department of Computer Science, University of North Carolina at Chapel Hill · New York University (NYU) · ELLIS Institute & MPI Intelligent Systems, Tübingen AI Center · University of Maryland
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work, we propose a universal guidance algorithm that enables diffusion models to be controlled by arbitrary guidance modalities without the need to retrain any use-specific components. We show that our algorithm successfully generates quality images with guidance functions including segmentation, face recognition, object detection, style guidance and classifier signals.