ALEXANDRIA, Va., June 19 -- United States Patent no. 12,334,116, issued on June 17, was assigned to University of Central Florida Research Foundation Inc. (Orlando, Fla.).

"Image diffusion framework for text-guided video editing" was invented by Nazmul Karim (Orlando, Fla.), Nazanin Rahnavard (Orlando, Fla.), Umar Khalid (Orlando, Fla.) and Chen Chen (Orlando, Fla.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The invention provides a method for adapting a text-to-image (T2I) diffusion model for video editing by using spectral decomposition to achieve controlled spectral shifts in the model's weights. This adaptation involves maintaining constant singular vectors while selectively adjusting singular values ...