US Patent Issued to Meta Platforms on Aug. 12 for "Scene-based text-to-image generation with human priors" (Israeli Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,387,388, issued on Aug. 12, was assigned to Meta Platforms Inc. (Menlo Park, Calif.).

"Scene-based text-to-image generation with human priors" was invented by Oran Gafni (Ramat Gan, Israel), Adam Polyak (Tel Aviv, Israel) and Yaniv Nechemia Taigman (Raanana, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "In one embodiment, a method includes accessing a text input and a scene input corresponding to the text input, wherein the scene input comprises semantic segmentations, generating text tokens for the text input and scene tokens for the scene input by machine-learning models, generating predicted image tokens based on the text tokens and the scene...