Universal Guidance for Diffusion Models
Arpit Bansal, Hongmin Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein
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, and classifier signals. Code is available at github.com/arpitbansal297/Universal-Guided-Diffusion.
Topics & Concepts
Computer scienceModalitiesArtificial intelligenceSegmentationDiffusionComputer visionSource codeClassifier (UML)Code (set theory)Pattern recognition (psychology)Social scienceOperating systemPhysicsProgramming languageThermodynamicsSociologySet (abstract data type)Generative Adversarial Networks and Image SynthesisAdvanced Neuroimaging Techniques and Applications3D Shape Modeling and Analysis