PERSONALIZED TEXT-TO-IMAGE DIFFUSION MODEL

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a text-to-image model so that the text-to-image model generates images that each depict a variable instance of an object class when the object class without the unique identifier is provided...

Full description

Saved in:
Bibliographic Details
Main Authors Ruiz Gutierrez, Nataniel, Jampani, Varun, Aberman, Kfir, Li, Yuanzhen, Pritch Knaan, Yael, Rubinstein, Michael
Format Patent
LanguageEnglish
Published 05.09.2024
Subjects
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a text-to-image model so that the text-to-image model generates images that each depict a variable instance of an object class when the object class without the unique identifier is provided as a text input, and that generates images that each depict a same subject instance of the object class when the unique identifier is provided as the text input.
Bibliography:Application Number: US202318569844