# US 2026/0073597 A1 · Techniques for Generating Dynamic Content

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

- Number: US 2026/0073597 A1
- Document ID: US20260073597A1
- Status: Published application
- Kind: A1
- Application number: 19/387,071
- Filed: 2025-11-12
- Published: 2026-03-12
- Earliest claimed: 2022-12-19
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Zebedee Pedersen; Luis De Jorge Ladrero; Marta Soto Morras; Kathryn Jane Strudwick
- Web page: https://patentgrep.com/patent/US20260073597A1

## CPC

- G06F 16/53: Querying
- G06T 11/60: Creating or editing images; Combining images with text
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A computer-implemented method for generating dynamic content. The method can include receiving, from an output of one or more machine-learned models, a first generated image. The first generated image can be generated based on a user query. Additionally, the method can include processing the first generated image, using the one or more machine-learned models, to determine a plurality of objects in the first generated image. Moreover, the method can include determining, using the one or more machine-learned models, a subset of actions associated with a first object in the plurality of objects. Furthermore, the method can include receiving a user input selecting a first action from the subset of actions associated with the first object. Subsequently, the method can include modifying the first object in the first generated image in response to the selection of the first action.

## Claims

### Claim 1

A computer-implemented method to generate dynamic content, the method comprising:
receiving, from an output of one or more machine-learned models, a first generated image, the first generated image being generated based on a user query;
processing the first generated image, using the one or more machine-learned models, to determine a plurality of objects in the first generated image;
determining, using the one or more machine-learned models, a subset of actions associated with a first object in the plurality of objects, wherein the subset of action is being determined based on a characteristic of the first object;
receiving a user input selecting a first action from the subset of actions associated with the first object; and
modifying a parameter of the one or more machine-learned model based on the user input.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
modifying the first object in the first generated image in response to the selection of the first action.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
modifying a second generated image in response to the selection of the first action, the second generated image being associated with the first generated image.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
presenting the subset of actions that can be performed to the first object in response to a selection of the first object.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
selecting the subset of actions from a larger set of actions based on a ranking score of each action in the larger set of actions.

### Claim 6 (depends on 1)

The method of claim 1, wherein the subset of actions is being determined based on a characteristic of the first object.

### Claim 7 (depends on 1)

The method of claim 1, wherein the generated image is generated by a machine-learned image generation model.

### Claim 8 (depends on 1)

The method of claim 1, wherein the plurality of objects in the generated image are determined by a machine-learned image segmentation model.

### Claim 9 (depends on 8)

The method of claim 8, wherein the machine-learned image segmentation model is a generative adversarial network (GAN) model that processes the first generated image to determine the first object.

### Claim 10 (depends on 1)

The method of claim 1, wherein the subset of actions is based on a semantic analysis, by the one or more machine-learned models, of content in the first generated image.

### Claim 11 (depends on 1)

The method of claim 1, wherein the subset of actions is based on a string text content of the user query.

### Claim 12 (depends on 1)

The method of claim 1, wherein the subset of actions includes deleting the first object.

### Claim 13 (depends on 1)

The method of claim 1, wherein the subset of actions includes changing a color of the first object.

### Claim 14 (depends on 1)

The method of claim 1, wherein the subset of actions includes moving the first object.

### Claim 15 (depends on 1)

The method of claim 1, wherein the subset of actions includes changing a shape of the first object.

### Claim 16 (depends on 1)

The method of claim 1, wherein the subset of actions includes changing a size of the first object.

### Claim 17 (depends on 1)

The method of claim 1, wherein the subset of actions includes changing a characteristic of the first object.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
in response to the selection of the first action from the subset of actions associated with the first object, determining, using the one or more machine-learned models, a plurality of sub-actions associated with the first action, the sub-actions being determined based on context of the first generated image, the first object, and the first action.

### Claim 19

A computer system, the system comprising:
one or more processors; and
one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
receiving, from an output of one or more machine-learned models, a first generated image, the first generated image being generated based on a user query;
processing the first generated image, using the one or more machine-learned models, to determine a plurality of objects in the first generated image;
determining, using the one or more machine-learned models, a subset of actions associated with a first object in the plurality of objects, wherein the subset of action is being determined based on a characteristic of the first object;
receiving a user input selecting a first action from the subset of actions associated with the first object; and
modifying a parameter of the one or more machine-learned model based on the user input.

### Claim 20

One or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause a computing system to perform operations, the operations comprising:
receiving, from an output of one or more machine-learned models, a first generated image, the first generated image being generated based on a user query;
processing the first generated image, using the one or more machine-learned models, to determine a plurality of objects in the first generated image;
determining, using the one or more machine-learned models, a subset of actions associated with a first object in the plurality of objects, wherein the subset of action is being determined based on a characteristic of the first object;
receiving a user input selecting a first action from the subset of actions associated with the first object; and
modifying a parameter of the one or more machine-learned model based on the user input.
