US Patent Issued to Adobe on July 28 for "Semantic mixing and style transfer utilizing a composable diffusion neural network" (California Inventors)

ALEXANDRIA, Va., July 28 -- United States Patent no. 12,694,484, issued on July 28, was assigned to Adobe Inc. (San Jose, Calif.).

"Semantic mixing and style transfer utilizing a composable diffusion neural network" was invented by Hareesh Ravi (San Jose, Calif.), Sachin Kelkar (Santa Clara, Calif.) and Ajinkya Gorakhnath Kale (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating digital images by conditioning a diffusion neural network with input prompts. In particular, in one or more embodiments, the disclosed systems generate, utilizing a reverse diffusion model, an image noise represen...