Poster
Universal Guidance for Diffusion Models
Arpit Bansal · Hong-Min Chu · Avi Schwarzschild · Roni Sengupta · Micah Goldblum · Jonas Geiping · Tom Goldstein
Halle B #41
Abstract:
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.
Chat is not available.