Presentation

· Contributors · Organizations · Search Program · My Schedule · Happening Now · Maps

Filter-Guided Diffusion for Controllable Image Generation

SessionControllable Image Generation and Completion

DescriptionFilter-Guided Diffusion (FGD) is a controllable, tuning-free, image-to-image translation method for diffusion models. It combines fast filtering operations with non-deterministic samplers to generate high-quality and diverse images. With its efficiency, FGD can be sampled multiple times to outperform previous methods in less time on structural and semantic metrics.

Authors

Zeqi Gu

Cornell-Tech Cornell University

Ethan Yang

Cornell University