US Patent Issued to ADOBE on Sept. 15 for "Text-based image generation using an image-trained text encoder" (California, Washington Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,933, issued on Sept. 15, was assigned to ADOBE INC. (San Jose, Calif.).

"Text-based image generation using an image-trained text encoder" was invented by Tobias Hinz (Campbell, Calif.), Ali Aminian (Piedmont, Calif.), Hao Tan (Santa Clara, Calif.), Kushal Kafle (Sunnyvale, Calif.), Oliver Wang (Seattle) and Jingwan Lu (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining a text prompt and encoding, using a text encoder jointly trained with an image generation model, the text prompt to obtain a text embedding. Some embodiments ...