公开(公告)号：US20250131604A1

公开(公告)日：2025-04-24

申请号：US18491472

申请日：2023-10-20

Applicant: ADOBE INC.

Inventor： Adrian-Stefan Ungureanu ,  Vlad-Constantin Lungu-Stan ,  Ionut Mironicã

IPC: G06T11/00 ,  G06F3/04845 ,  G06F3/04847

Abstract: Embodiments include obtaining a prompt and a diversity input indicating a level of adherence to the prompt. The diversity input may be implemented as a graphical user interface (GUI) element, such as a slider or field. Embodiments then generate a guidance embedding based on the prompt and the diversity input. Embodiments update the guidance embedding based on the diversity input. Subsequently, embodiments generate a synthetic image based on the guidance embedding, wherein the synthetic image depicts an element of the prompt based on the level of adherence from the diversity input.

公开(公告)号：US12118647B2

公开(公告)日：2024-10-15

申请号：US17405207

申请日：2021-08-18

Applicant: Adobe Inc.

Inventor： Adrian-Stefan Ungureanu ,  Ionut Mironica ,  Richard Zhang

IPC: G06T11/00 ,  G06N3/04

CPC classification number: G06T11/001 ,  G06N3/04

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize one or more stages of a two-stage image colorization neural network to colorize or re-colorize digital images. In one or more embodiments, the disclosed system generates a color digital image from a grayscale digital image by utilizing a colorization neural network. Additionally, the disclosed system receives one or more inputs indicating local hints comprising one or more color selections to apply to one or more objects of the color digital image. The disclosed system then utilizes a re-colorization neural network to generate a modified digital image from the color digital image by modifying one or more colors of the object(s) based on the luminance channel, color channels, and selected color(s).

公开(公告)号：US20240386707A1

公开(公告)日：2024-11-21

申请号：US18319731

申请日：2023-05-18

Applicant: Adobe Inc.

Inventor： Adrian-Stefan Ungureanu ,  Marian Lupascu ,  Ionut Mironicá

IPC: G06V10/776 ,  G06F40/40 ,  G06T11/00 ,  G06V10/74 ,  G06V10/774

Abstract: In implementations of systems for evaluating bias in generative models, a computing device implements a bias system to generate a modified digital image by processing an input digital image using a first machine learning model trained on training data to generate modified digital images based on input digital images. The bias system computes a first latent representation of the input digital image and a second latent representation of the modified digital image using a second machine learning model trained on training data to compute latent representations of digital images. A bias score is determined for a visual attribute based on the first latent representation and the second latent representation. The bias system generates an indication of the bias score for the visual attribute for display in a user interface.

公开(公告)号：US20230055204A1

公开(公告)日：2023-02-23

申请号：US17405207

申请日：2021-08-18

Applicant: Adobe Inc.

Inventor： Adrian-Stefan Ungureanu ,  Ionut Mironica ,  Richard Zhang

IPC: G06T11/00 ,  G06N3/04

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize one or more stages of a two-stage image colorization neural network to colorize or re-colorize digital images. In one or more embodiments, the disclosed system generates a color digital image from a grayscale digital image by utilizing a colorization neural network. Additionally, the disclosed system receives one or more inputs indicating local hints comprising one or more color selections to apply to one or more objects of the color digital image. The disclosed system then utilizes a re-colorization neural network to generate a modified digital image from the color digital image by modifying one or more colors of the object(s) based on the luminance channel, color channels, and selected color(s).