US Patent Issued to Salesforce on March 24 for "Systems and methods for text-to-image generation using language models" (California, Massachusetts Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,585,919, issued on March 24, was assigned to Salesforce Inc. (San Francisco).

"Systems and methods for text-to-image generation using language models" was invented by Ning Yu (Palo Alto, Calif.), Can Qin (Somervile, Mass.), Chen Xing (Palo Alto, Calif.), Shu Zhang (Fremont, Calif.), Stefano Ermon (Menlo Park, Calif.), Caiming Xiong (Menlo Park, Calif.) and Ran Xu (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments described herein provide a mechanism for replacing existing text encoders in text-to-image generation models with more powerful pre-trained language models. Specifically, a translation network is trained to map f...