ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,411, issued on Nov. 3, was assigned to ADOBE INC. (San Jose, Calif.).

"Embedding an input image to a diffusion model" was invented by Yosef Gandelsman (Berkeley, Calif.), Taesung Park (San Francisco), Richard Zhang (Burlingame, Calif.) and Elya Shechtman (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for image editing are described. Embodiments of the present disclosure include obtaining an image and a prompt for editing the image. A diffusion model is tuned based on the image to generate different versions of the image. The prompt is then encoded to obtain a guidance vector, and the diffusion model generates a modified i...