US Patent Issued to Nvidia on Jan. 13 for "Synthesizing content using diffusion models in content generation systems and applications" (Canadian, American Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,845, issued on Jan. 13, was assigned to Nvidia Corp. (Santa Clara, Calif.).

"Synthesizing content using diffusion models in content generation systems and applications" was invented by Karsten Julian Kreis (Vancouver, Canada), Tim Dockhorn (Vancouver, Canada) and Arash Vahdat (San Mateo, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Approaches presented herein provide for the generation of synthesized data from input noise using a denoising diffusion network. A higher order differential equation solver can be used for the denoising process, with one or more higher-order terms being distilled into one or more separate efficient neural network...