计算机科学
模式
人工智能
分割
源代码
扩散
分类器(UML)
计算机视觉
编码(集合论)
再培训
模式识别(心理学)
物理
热力学
社会科学
集合(抽象数据类型)
社会学
国际贸易
业务
程序设计语言
操作系统
作者
Ankit Bansal,Hongmin Chu,Avi Schwarzschild,Shamik Sengupta,Micah Goldblum,Jonas Geiping,Tom Goldstein
标识
DOI:10.1109/cvprw59228.2023.00091
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, and classifier signals. Code is available at github.com/arpitbansal297/Universal-Guided-Diffusion.
科研通智能强力驱动
Strongly Powered by AbleSci AI