IP Library › Granted Patent US 12,675,818
Granted Patent B2
US 12,675,818 · App. 18/219,527 · Granted Jul 7, 2026

Product as a key for context-based image generation

Inventors: Matthew Difonzo (Belmont, CA); Leslie Young Harvill (Olympia, WA)
Assignee: Zazzle Inc.
G06T11/60G06Q30/0621G06T2210/16
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,675,818
App. No.
18/219,527
Filed
Jul 7, 2023
Granted
Jul 7, 2026
Kind
B2
Art Unit
2611
USPC
345/634
Abstract

In some embodiments, a method for using a custom product as a key for context-based image generation comprises: receiving, by a visualization service of a computer collaboration system, a graphical representation of a custom digital product; determining one or more regions for customizing regions; for a region of the regions: determining a set of phrases that are specific to the custom digital product and a customization process for customizing the custom digital product; based on the set of phrases, generating a synthetic image generation request; transmitting request to an AI based image generator configured to generate synthetic images; causing the AI-based generator to: generate a customized synthetic image based on the request and a repository of images; wherein the customized synthetic image is not a copy of any image from the repository of images; transmit the customized synthetic image to the computer collaboration system; including the image in the region; causing displaying the graphical visualization of the custom digital product along with the customized synthetic image in the region.

Claims (79)

1 . A method for using a custom product as a key for context-based image generation, the method comprising:

receiving, by a visualization service of a computer collaboration system, a graphical representation of a custom digital product;

determining, by the visualization service, one or more regions for customizing regions when displaying a graphical visualization of the custom digital product on a display device;

for a region of the one or more regions:

determining, by the visualization service, a set of phrases that are specific to the custom digital product and a customization process for customizing the custom digital product; wherein the set of phrases comprises one or more pieces of information extracted from a user profile of a user who customized the custom digital product;

based on the set of phrases, generating a synthetic image generation request;

transmitting the synthetic image generation request to an artificial intelligence (AI) based image generator configured to generate synthetic images;

causing the AI-based generator to:

generate a customized synthetic image based on, at least in part, the synthetic image generation request and a repository of images; wherein the customized synthetic image is not a copy of any image from the repository of images;

transmit the customized synthetic image to the computer collaboration system;

including the customized synthetic image in the region;

causing displaying, on the display device, the graphical visualization of the custom digital product along with the customized synthetic image in the region.

2 . The method of claim 1 , wherein the graphical representation of the custom digital product is constructed using a series of rendering and compositing actions derived from product description data for a custom digital product;

wherein the compositing actions include manufacturing instructions;

wherein the product description data comprise a plurality of parameters of the custom digital product;

wherein each parameter, of the plurality of parameters of the custom product, is a key-value pair;

wherein the key-value pair is a data structure that includes an attribute key and a corresponding attribute value.

3 . The method of claim 2 , wherein the set of phrases comprises one or more key-value pairs extracted from the product description data.

4 . The method of claim 2 , wherein the set of phrases comprises one or more pieces of information extracted from a repository of events associated with the custom digital product.

5 . The method of claim 2 , wherein the customized synthetic image is generated by synthesizing two or more images extracted from the repository of images that are tagged with phrases matching one or more phrases in the set of phrases;

wherein images in the repository of images are tagged using corresponding tags;

wherein the customized synthetic image is generated contemporaneously by updating a display of the custom digital product on the display device.

6 . The method of claim 1 , further comprising:

transmitting the graphical representation of the custom digital product to a manufacturing product rendering unit;

causing the manufacturing product rendering unit to:

render the graphical representation of the custom digital product;

print, using one or more printing instructions of a manufacturing product rendering unit, the graphical representation of the custom digital product to generate a physical representation of the custom digital product.

7 . One or more non-transitory computer-readable media storing one or more instructions, which, when executed by one or more processors, cause the one or more processors to perform:

receiving, by a visualization service of a computer collaboration system, a graphical representation of a custom digital product;

determining, by the visualization service, one or more regions for customizing regions when displaying a graphical visualization of the custom digital product on a display device;

for a region of the one or more regions:

determining, by the visualization service, a set of phrases that are specific to the custom digital product and a customization process for customizing the custom digital product; wherein the set of phrases comprises one or more pieces of information extracted from a user profile of a user who customized the custom digital product;

based on the set of phrases, generating a synthetic image generation request;

transmitting the synthetic image generation request to an artificial intelligence (AI) based image generator configured to generate synthetic images;

causing the AI-based generator to:

generate a customized synthetic image based on, at least in part, the synthetic image generation request and a repository of images; wherein the customized synthetic image is not a copy of any image from the repository of images;

transmit the customized synthetic image to the computer collaboration system;

including the customized synthetic image in the region;

causing displaying, on the display device, the graphical visualization of the custom digital product along with the customized synthetic image in the region.

8 . The one or more non-transitory computer-readable media of claim 7 , wherein the graphical representation of the custom digital product is constructed using a series of rendering and compositing actions derived from product description data for a custom digital product;

wherein the compositing actions include manufacturing instructions;

wherein the product description data comprise a plurality of parameters of the custom digital product;

wherein each parameter, of the plurality of parameters of the custom product, is a key-value pair;

wherein the key-value pair is a data structure that includes an attribute key and a corresponding attribute value.

9 . The one or more non-transitory computer-readable media of claim 8 , wherein the set of phrases comprises one or more key-value pairs extracted from the product description data.

10 . The one or more non-transitory computer-readable media of claim 8 , wherein the set of phrases comprises one or more pieces of information extracted from a repository of events associated with the custom digital product.

11 . The one or more non-transitory computer-readable media of claim 8 , wherein the customized synthetic image is generated by synthesizing two or more images extracted from the repository of images that are tagged with phrases matching one or more phrases in the set of phrases;

wherein images in the repository of images are tagged using corresponding tags;

wherein the customized synthetic image is generated contemporaneously by updating a display of the custom digital product on the display device.

12 . The one or more non-transitory computer-readable media of claim 8 , further comprising:

transmitting the graphical representation of the custom digital product to a manufacturing product rendering unit;

causing the manufacturing product rendering unit to:

render the graphical representation of the custom digital product;

print, using one or more printing instructions of a manufacturing product rendering unit, the graphical representation of the custom digital product to generate a physical representation of the custom digital product.

13 . A custom product computer system generator comprising:

a memory unit;

one or more processors; and

a custom product computer storing one or more instructions, which, when executed by one or more processors, cause the one or more processors to perform:

receiving, by a visualization service of a computer collaboration system, a graphical representation of a custom digital product;

determining, by the visualization service, one or more regions for customizing regions when displaying a graphical visualization of the custom digital product on a display device;

for a region of the one or more regions:

determining, by the visualization service, a set of phrases that are specific to the custom digital product and a customization process for customizing the custom digital product; wherein the set of phrases comprises one or more pieces of information extracted from a user profile of a user who customized the custom digital product;

based on the set of phrases, generating a synthetic image generation request;

transmitting the synthetic image generation request to an artificial intelligence (AI) based image generator configured to generate synthetic images;

causing the AI-based generator to:

generate a customized synthetic image based on, at least in part, the synthetic image generation request and a repository of images; wherein the customized synthetic image is not a copy of any image from the repository of images;

transmit the customized synthetic image to the computer collaboration system;

including the customized synthetic image in the region;

causing displaying, on the display device, the graphical visualization of the custom digital product along with the customized synthetic image in the region.

14 . The custom product computer system generator of claim 13 , wherein the graphical representation of the custom digital product is constructed using a series of rendering and compositing actions derived from product description data for a custom digital product;

wherein the compositing actions include manufacturing instructions;

wherein the product description data comprise a plurality of parameters of the custom digital product;

wherein each parameter, of the plurality of parameters of the custom product, is a key-value pair;

wherein the key-value pair is a data structure that includes an attribute key and a corresponding attribute value.

15 . The custom product computer system generator of claim 14 , wherein the set of phrases comprises one or more key-value pairs extracted from the product description data.

16 . The custom product computer system generator of claim 14 , wherein the set of phrases comprises one or more pieces of information extracted from a repository of events associated with the custom digital product.

17 . The custom product computer system generator of claim 14 , wherein the customized synthetic image is generated by synthesizing two or more images extracted from the repository of images that are tagged with phrases matching one or more phrases in the set of phrases;

wherein images in the repository of images are tagged using corresponding tags;

wherein the customized synthetic image is generated contemporaneously by updating a display of the custom digital product on the display device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 18, 2023
From: DIFONZO, MATTHEW; HARVILL, LESLIE YOUNG
To: ZAZZLE INC.
Reel/Frame 064303/0477 →
Continuity (1)
Related Publication 20250014246A1 · Jan 9, 2025
References Cited (17)
US 20130060801A1 · Beaver, III · 2013 [cited by examiner]
US 20170017647A1 · Musuluri · 2017 [cited by examiner]
US 20190050427A1 · Wiesel · 2019 [cited by examiner]
US 20200159871A1 · Bowen · 2020 [cited by examiner]
US 20210272341A1 · Swaminathan · 2021 [cited by examiner]
KR 20230012243A · 2023 [cited by applicant]
KR 102539376B1 · 2023 [cited by applicant]
Gdpicture.com, “Introduction to the New Key-Value Pair Data Extractor for the OCR Engine”, https://www.gdpicture.com/blog/new-key-value-pair-data-extractor-ocr-engine, Jun. 20, 2022 (Year: 2022). [cited by examiner]
“Stable Diffusion is a text-to-image AI thats much more accessible than its predecessors”, Anyone can use this AI art generator—thats a risk. Sep. 15, 2022. https://www.theverge.com/2022/9/15/23340673/ai-image-generatio… [cited by applicant]
“Using software that creates art on demand, some artists attempt to cash in on Algenerated Content”, Artists begin selling AI-generated artwork on stock photography websites. Sep. 16, 2022. https://arstechnica.com/infor… [cited by applicant]
Stable Diffusion, A latent text-to-image diffusion model. https://github.com/CompVis/stable-diffusion. Nov. 16, 2022. [cited by applicant]
How does Stable Diffusion work?—LatentDiffusion Models EXPLAINED. YouTube. https://www.youtube.com/watch?v=J87hffSMB60. Date pulled Jul. 7, 2023. [cited by applicant]
Stable Diffusion is a really big deal, Simon Willson's Weblog.https://simonwillison.net/2022/Aug/29/stable-diffusion/ . Aug. 29, 2022. [cited by applicant]
With Stable Diffusion, you may never believe what you see online again, AI image synthesis goes open source, with big implications. Benj Edwards / Stable Diffusion Sep. 6, 2022. [cited by applicant]
Extended European Search Report for European Patent Application No. 24173362.5, dated Oct. 29, 2024. [cited by applicant]
Koukoumidis Emmanouil et al: “AI-based Image Synthesis for Enriched Search and Shopping AI-based Image Synthesis for Enriched Search and Shopping”, Technical Disclosure Commons, Jun. 8, 2021 (Jun. 8, 2021), XP055960246,… [cited by applicant]
European Search Report dated Oct. 14, 2024 for Application No. EP 24 17 3362. [cited by applicant]