US 12,462,456 B2
Non-destructive generative image editing
Davis Taylor Brown, Seattle, WA (US); Alan Lee Erickson, Franktown, CO (US); Dana Michelle Jefferson, Astoria, NY (US); and Michael Spencer Cragg, Troy, MI (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jun. 5, 2023, as Appl. No. 18/329,058.
Claims priority of provisional application 63/503,057, filed on May 18, 2023.
Prior Publication US 2024/0386634 A1, Nov. 21, 2024
Int. Cl. G06T 11/60 (2006.01); G06F 40/166 (2020.01)
CPC G06T 11/60 (2013.01) [G06F 40/166 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, via a document editor user interface, a selection input identifying a portion of a first image displayed in the document editor user interface, wherein the first image is part of a first layer of a multilayer document;
obtaining, via the document editor user interface, an image generation text prompt;
generating, using an image generation network, a second image based on the first image, an input mask corresponding to the portion of the first image identified by the selection input, and the image generation text prompt;
generating a subject mask by detecting an object in the second image; and
presenting, via a multilayer window of the document editor user interface, a first element representing the first layer of the multilayer document and a second element representing a second layer of the multilayer document, wherein the first element presents the first image and the second element presents the second image and the subject mask generated based on the second image.