ALEXANDRIA, Va., Nov. 6 -- United States Patent no. 12,462,348, issued on Nov. 4, was assigned to ADOBE INC. (San Jose, Calif.).
"Multimodal diffusion models" was invented by Cusuh Ham (Marietta, Ga.), Tobias Hinz (Campbell, Calif.), Jingwan Lu (Sunnyvale, Calif.), Krishna Kumar Singh (San Jose, Calif.) and Zhifei Zhang (San Jose, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for image processing are described. Embodiments of the present disclosure obtain a noise image and guidance information for generating an image. A diffusion model generates an intermediate noise prediction for the image based on the noise image. A conditioning network generates noise modulation parameters. Th...