公开(公告)号：US20240355017A1

公开(公告)日：2024-10-24

申请号：US18302508

申请日：2023-04-18

Applicant: Google LLC

Inventor： Shiran Elyahu Zada ,  Bahjat Kawar ,  Oran Lang ,  Omer Tov ,  Huiwen Chang ,  Tali Dekel ,  Inbar Mosseri

IPC: G06T11/60 ,  G06T3/40

CPC classification number: G06T11/60 ,  G06T3/4053

Abstract: Methods and systems for editing an image are disclosed herein. The method includes receiving an input image and a target text, the target text indicating a desired edit for the input image and obtaining, by the computing system, a target text embedding based on the target text. The method also includes obtaining, by the computing system, an optimized text embedding based on the target text embedding and the input image and fine-tuning, by the computing system, a diffusion model based on the optimized text embedding. The method can further include interpolating, by the computing system, the target text embedding and the optimized text embedding to obtain an interpolated embedding and generating, by the computing system, an edited image including the desired edit using the diffusion model based on the input image and the interpolated embedding.