18890203. IN-CONTEXT IMAGE GENERATION USING STYLE IMAGES (ADOBE INC.)

From WikiPatents
Jump to navigation Jump to search

IN-CONTEXT IMAGE GENERATION USING STYLE IMAGES

Organization Name

ADOBE INC.

Inventor(s)

Vlad-Constantin Lungu-stan of Bucuresti RO

Marian Lupascu of Bucuresti RO

[[:Category:Ionut Mironic� of Bucharest RO|Ionut Mironic� of Bucharest RO]][[Category:Ionut Mironic� of Bucharest RO]]

IN-CONTEXT IMAGE GENERATION USING STYLE IMAGES

This abstract first appeared for US patent application 18890203 titled 'IN-CONTEXT IMAGE GENERATION USING STYLE IMAGES

Original Abstract Submitted

A method, apparatus, non-transitory computer readable medium, and system for generating images with a particular style that fit coherently into a scene includes obtaining a text prompt and a preliminary style image. The text prompt describes an image element, and the preliminary style image includes a region with a target style. Embodiments then extract the region with the target style from the preliminary style image to obtain a style image. Embodiments subsequently generate, using an image generation model, a synthetic image based on the text prompt and the style image. The synthetic image depicts the image element with the target style.