公开(公告)号：US20240338870A1

公开(公告)日：2024-10-10

申请号：US18479379

申请日：2023-10-02

Applicant: ADOBE INC.

Inventor： Siddharth Iyer ,  David Davenport Bourgin ,  Sudeep Katakol ,  Aliakbar Darabi

IPC: G06T11/60

CPC classification number: G06T11/60 ,  G06T2200/24

Abstract: A method, apparatus, and non-transitory computer readable medium for image generation are described. Embodiments of the present disclosure obtain, via a user interface, an input text. The user interface also obtains a text effect prompt that describes a text effect for the input text. An image generation model generates an output image depicting the input text with the text effect described by the text effect prompt.

公开(公告)号：US20240338829A1

公开(公告)日：2024-10-10

申请号：US18500263

申请日：2023-11-02

Applicant: ADOBE INC.

Inventor： Sudeep Katakol ,  Siddharth Iyer ,  Aliakbar Darabi

IPC: G06T7/194 ,  G06T7/11 ,  G06T11/60

CPC classification number: G06T7/194 ,  G06T7/11 ,  G06T11/60 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20212

Abstract: Embodiments of the present disclosure include obtaining an input image and an approximate mask that approximately indicates a foreground region of the input image. Some embodiments generate an unconditional mask of the foreground region based on the input image. A conditional mask of the foreground region is generated based on the input image and the approximate mask. Then, an output image is generated based on the unconditional mask and the conditional mask. In some cases, the output image includes the foreground region of the input image.