# US 2025/0095222 A1 · Generating and presenting content using a generative artificial intelligence model

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0095222 A1
- Document ID: US20250095222A1
- Status: Published application
- Kind: A1
- Application number: 18/468,313
- Filed: 2023-09-15
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Audiotrocities LLC
- Applicants: Audiotrocities LLC
- Inventors: GLENN E. SUGDEN
- Web page: https://patentgrep.com/patent/US20250095222A1

## CPC

- G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information}
- G06T 11/00: Two-dimensional [2D] image generation
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 16/532: Query formulation, e.g. graphical querying
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image generation system may receive a set of descriptors. An image generation system may generate a prompt input using the set of descriptors. An image generation system may apply a prompt generator model to the prompt input to generate an image prompt for a generative artificial intelligence (AI) model, wherein the image prompt includes a context generated based on the set of descriptors, wherein the image prompt includes a prompt format configured to be input into the generative AI model. An image generation system may input the image prompt to the generative AI model, the generative AI model using the image prompt to generate an image based on the context.

## Claims

### Claim 1

A method, comprising:
receiving a set of descriptors;
generating a prompt input using the set of descriptors;
applying a prompt generator model to the prompt input to generate an image prompt for a generative artificial intelligence (AI) model, wherein the image prompt includes a context generated based on the set of descriptors, wherein the image prompt includes a prompt format configured to be input into the generative AI model; and
inputting the image prompt to the generative AI model, the generative AI model using the image prompt to generate an image based on the context.

### Claim 2 (depends on 1)

The method of claim 1, wherein the prompt format includes a plurality of factors, the plurality of factors based on preferred inputs for the generative AI model.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
providing the image prompt to a user; and
revising the image prompt based on feedback from the user.

### Claim 4 (depends on 1)

The method of claim 1, wherein at least one of the set of descriptors include an end-use for the image.

### Claim 5 (depends on 1)

The method of claim 1, wherein generating the image prompt includes generating the image prompt using a prompt AI model.

### Claim 6 (depends on 1)

The method of claim 1, wherein the generative AI model generates a plurality of images using the image prompt.

### Claim 7 (depends on 1)

The method of claim 1, further comprising applying the image as a background image of a user device.

### Claim 8 (depends on 1)

The method of claim 1, wherein receiving the set of descriptors includes receiving a selection from a user of at least one descriptor of the set of descriptors.

### Claim 9 (depends on 1)

The method of claim 1, wherein receiving the set of descriptors includes identifying descriptors from media content.

### Claim 10

A system, comprising:
a processor and memory, the memory including instructions that cause a processor to:
receive a set of descriptors;
generate a prompt input using the set of descriptors;
apply a prompt generator model to the prompt input to generate an image prompt for a generative artificial intelligence (AI) model, wherein the image prompt includes a context generated based on the set of descriptors, wherein the image prompt includes a prompt format configured to be input into the generative AI model; and
input the image prompt to the generative AI model, the generative AI model using the image prompt to generate an image based on the context.

### Claim 11 (depends on 10)

The system of claim 10, wherein the prompt format includes a plurality of factors, the plurality of factors based on preferred inputs for the generative AI model.

### Claim 12 (depends on 10)

The system of claim 10, wherein the instructions further cause the processor to:
provide the image prompt to a user; and
revise the image prompt based on feedback from the user.

### Claim 13 (depends on 10)

The system of claim 10, wherein at least one of the set of descriptors include an end-use for the image.

### Claim 14 (depends on 10)

The system of claim 10, wherein generating the image prompt includes generating the image prompt using a prompt AI model.

### Claim 15 (depends on 10)

The system of claim 10, wherein the generative AI model generates a plurality of images using the image prompt.

### Claim 16 (depends on 10)

The system of claim 10, wherein the instructions further cause the processor to apply the image as a background image of a user device.

### Claim 17 (depends on 10)

The system of claim 10, wherein receiving the set of descriptors includes receiving a selection from a user of at least one descriptor of the set of descriptors.

### Claim 18 (depends on 10)

The system of claim 10, wherein receiving the set of descriptors includes identifying descriptors from media content.

### Claim 19

A method, comprising:
receiving a set of descriptors that describe factors of an image;
generating a prompt input using the set of descriptors;
applying a prompt generator model to the prompt input to generate a dynamic image prompt for a generative artificial intelligence (AI) model, wherein the dynamic image prompt includes a context generated based on the set of descriptors, wherein the dynamic image prompt includes a prompt format configured to be input into the generative AI model;
revising the dynamic image prompt based on user input; and
inputting the image prompt to the generative AI model, the generative AI model using the image prompt to generate an image based on the context.

### Claim 20 (depends on 19)

The method of claim 19, wherein revising the dynamic image prompt includes receiving revisions to one or more factors included in text of the dynamic image prompt.
