Presentation / Installation
Zero-shot Image-to-image Translation
SessionImage and Video Editing
DescriptionWe propose pix2pix-zero, a diffusion-based, image-to-image approach that allows for specifying the edit direction on the fly (e.g., cat to dog). Our method can directly use pre-trained text-to-image diffusion models, such as Stable Diffusion, for editing real and synthetic images while preserving the input image's structure. Our method is training free and prompt free.
Event Type
Technical Paper
TimeMonday, 7 August 20232:44pm - 2:54pm PDT
LocationPetree Hall D
ACM Digital Library
Technical Paper PDF
Session Time & Location
Research & Education
Livestreamed
Recorded
FC
FCS
V
VS
EFC