公开(公告)号：US20240161462A1

公开(公告)日：2024-05-16

申请号：US18053556

申请日：2022-11-08

Applicant: ADOBE INC.

Inventor： Yosef Gandelsman ,  Taesung Park ,  Richard Zhang ,  Elya Shechtman

IPC: G06V10/774 ,  G06T5/00 ,  G06T11/00 ,  G06V10/776 ,  G06V10/82 ,  G06V10/94

CPC classification number: G06V10/774 ,  G06T5/002 ,  G06T11/00 ,  G06V10/776 ,  G06V10/82 ,  G06V10/945 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for image editing are described. Embodiments of the present disclosure include obtaining an image and a prompt for editing the image. A diffusion model is tuned based on the image to generate different versions of the image. The prompt is then encoded to obtain a guidance vector, and the diffusion model generates a modified image based on the image and the encoded text prompt.

公开(公告)号：US20240169604A1

公开(公告)日：2024-05-23

申请号：US18057453

申请日：2022-11-21

Applicant: ADOBE INC.

Inventor： Yosef Gandelsman ,  Taesung Park ,  Richard Zhang ,  Elya Shechtman ,  Alexei A. Efros

IPC: G06T11/00 ,  G06F3/04842 ,  G06F3/04845 ,  G06T11/20

CPC classification number: G06T11/001 ,  G06F3/04842 ,  G06F3/04845 ,  G06T11/20

Abstract: Systems and methods for image generation are described. Embodiments of the present disclosure obtain user input that indicates a target color and a semantic label for a region of an image to be generated. The system also generates of obtains a noise map including noise biased towards the target color in the region indicated by the user input. A diffusion model generates the image based on the noise map and the semantic label for the region. The image can include an object in the designated region that is described by the semantic label and that has the target color.