US Patent Issued to AMAZON TECHNOLOGIES on July 14 for "Machine learning systems for generating output images based on style elements of input images" (Washington, California Inventors)

ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,511, issued on July 14, was assigned to AMAZON TECHNOLOGIES INC. (Seattle).

"Machine learning systems for generating output images based on style elements of input images" was invented by Silviu Stefan Andrei (Kirkland, Wash.), Guanglei Xiong (Pleasanton, Calif.) and Tor Hamilton Steiner (Redmond, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A diffusion model is provided with a reference image and a text prompt, and generates output images having content specified in the prompt and style characteristics represented in the image. The reference image is encoded to generate multiple image embeddings. The prompt is encoded to generate a text emb...