US Patent Issued to Google on Aug. 25 for "Fine-tuning diffusion-based generative neural networks using singular value decompositions for text-to-image generation" (California, New Jersey Inventors)

ALEXANDRIA, Va., Aug. 25 -- United States Patent no. 12,718,438, issued on Aug. 25, was assigned to Google LLC (Mountain View, Calif.).

"Fine-tuning diffusion-based generative neural networks using singular value decompositions for text-to-image generation" was invented by Yinxiao Li (Sunnyvale, Calif.), Ligong Han (Edison, N.J.), Han Zhang (Sunnyvale, Calif.), Peyman Milanfar (Menlo Park, Calif.) and Feng Yang (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for fine-tuning diffusion-based generative neural networks in compact parameter spaces for text-to-image generation. In one aspect, a met...