US Patent Issued to Adobe on May 19 for "Text-to-image synthesis utilizing diffusion models with test-time attention segregation and retention optimization" (Indian Inventors)

ALEXANDRIA, Va., May 19 -- United States Patent no. 12,633,000, issued on May 19, was assigned to Adobe Inc. (San Jose, Calif.).

"Text-to-image synthesis utilizing diffusion models with test-time attention segregation and retention optimization" was invented by Aishwarya Agarwal (Bengaluru, India), Srikrishna Karanam (Bangalore, India), Joseph Koonthanam Jose (Kottayam, India), Apoorv Umang Saxena (Bengaluru, India), Koustava Goswami (Bangalore, India) and Balaji Vasan Srinivasan (Bangalore, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilizes attention segregation loss and/or attention retention loss...