Generation of brand-aligned product images

Patent metadata

Field	Value
Publication number	US-2026044992-A1
Application number	US-202418797166-A
Country	US
Kind code	A1
Filing date	Aug 7, 2024
Priority date	Aug 7, 2024
Publication date	Feb 12, 2026
Grant date	—

Abstract

Methods, computer systems, computer storage media, and graphical user interfaces are provided for facilitating generation of brand-aligned product images. In one implementation, a product-environment prompt including a text description of a reference image is obtained. Further, a set of image features extracted from the reference image is obtained. Thereafter, a brand-aligned product image is generated by performing outpainting from a product representation in accordance with the product-environment prompt and the set of image features extracted from the reference image. The brand-aligned product image can then be provided for display via a graphical user interface.

First claim

What is claimed is:

1 . One or more computer storage media having computer-executable instructions embodied thereon that, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:
obtaining a product-environment prompt including a text description of a reference image; obtaining a set of image features extracted from the reference image; generating a brand-aligned product image by performing outpainting from a product representation in accordance with the product-environment prompt and the set of image features extracted from the reference image; and providing, for display via a graphical user interface, the brand-aligned product image.

2 . The media of claim 1 , wherein the text description describes a composition associated with the reference image, a scene associated with the reference image, a color associated with the reference image, a style of shot associated with the reference image, or a combination thereof.

3 . The media of claim 1 , wherein the reference image is selected from among a set of candidate reference images identified based on a search performed using a user-selected theme.

4 . The media of claim 1 , wherein the product-environment prompt is generated using a set of responses generated by a large multimodal model based on input including the reference image and one or more instructions requesting descriptions of image components associated with the reference model.

5 . The media of claim 1 , wherein the set of image features are extracted from the reference image using a diffusion model.

6 . The media of claim 1 , wherein the set of image features represent lighting, textures, shapes, edges, or a combination thereof.

7 . The media of claim 1 , wherein outpainting is performed using a diffusion model.

8 . The media of claim 1 , wherein generating the brand-aligned product image further comprises applying fidelity preservation through generation in association with the product representation.

9 . The media of claim 1 , wherein generating the brand-aligned product image further comprises applying artifact removal in association with the product representation.

10 . The media of claim 1 further comprising:
receiving user feedback approving or disapproving of the brand-aligned product image; and
updating the brand-aligned product image based on the user feedback.

11 . A computer-implemented method comprising:
obtaining a reference image desired to be used as a source of inspiration for a background setting for a product representation; generating a product-environment prompt including a text description of the reference image by inputting the reference image into a large multimodal model with an instruction to generate the text description of the reference image; and using the product-environment prompt to generate a brand-aligned product image that includes the product representation placed within a background outpainted, via a diffusion model, in accordance with the text description of the reference image.

12 . The method of claim 11 , wherein the reference image is selected from among a set of candidate reference images identified as matching a desired theme for the background setting for the product representation.

13 . The method of claim 11 , wherein the reference image aligns with a brand associated with the product representation.

14 . The method of claim 11 , wherein the text description of the reference image describes a composition of the reference image, a scene of the reference image, a color of the reference image, a style of shot of the reference image, or a combination thereof.

15 . The method of claim 11 , wherein generation of the brand-aligned product image further uses a set of image features extracted from the image via the diffusion model.

16 . A computing system comprising:
a processor; and one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, causes the one or more processors to perform operations comprising:
obtaining a product representation;
providing, as input to a diffusion model, the product representation, a reference image, and a product-environment prompt indicating a text description of a reference image; and
obtaining, as output from the diffusion model, an outpainted image that includes a background outpainted in association with the product representation in accordance with the product-environment prompt and a set of image features extracted from the reference image.

17 . The system of claim 16 , further comprising applying fidelity preservation through generation in association with the product representation in the outpainted image.

18 . The system of claim 16 , further comprising applying artifact removal in association with the product representation in the outpainted image.

19 . The system of claim 16 , further comprising providing, for display, the outpainted image or a modified version thereof.

20 . The system of claim 19 further comprising:
receiving user feedback associated with the displayed outpainted image or the modified version thereof; and
updating the outpainted image or the modified version thereof based on the user feedback.

Assignees

• Adobe Inc

Inventors

• Agarwal Dhwanit
• Moorarka Umang
• Agrawal Shradha
• Reddy Vangala Naveen
• Revanur Ambareesh

Classifications

• G06T7/11

  Region-based segmentation · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06T2211/441

  AI-based methods, deep learning or artificial neural networks · CPC title

• G06T11/00 Primary

  Two-dimensional [2D] image generation · CPC title