公开(公告)号：US20240169622A1

公开(公告)日：2024-05-23

申请号：US18057851

申请日：2022-11-22

Applicant: ADOBE INC.

Inventor： Shaoan Xie ,  Zhifei Zhang ,  Zhe Lin ,  Tobias Hinz

IPC: G06T11/60 ,  G06T7/11 ,  G06T11/00

CPC classification number: G06T11/60 ,  G06T7/11 ,  G06T11/001 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for multi-modal image editing are provided. In one aspect, a system and method for multi-modal image editing includes identifying an image, a prompt identifying an element to be added to the image, and a mask indicating a first region of the image for depicting the element. The system then generates a partially noisy image map that includes noise in the first region and image features from the image in a second region outside the first region. A diffusion model generates a composite image map based on the partially noisy image map and the prompt. In some cases, the composite image map includes the target element in the first region that corresponds to the mask.