# US 2025/0148674 A1 · Conversation-specific image generation based on prompts

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

- Number: US 2025/0148674 A1
- Document ID: US20250148674A1
- Status: Published application
- Kind: A1
- Application number: 18/982,758
- Filed: 2024-12-16
- Published: 2025-05-08
- Earliest claimed: 2023-03-01
- Assignees: Snap Inc.
- Applicants: Snap Inc.
- Inventors: Sergey Smetanin; Arnab Ghosh; Pavel Savchenkov; Jian Ren; Sergey Tulyakov; Ivan Babanin; Timur Zakirov; Roman Golobokov; Aleksandr Zakharov; Dor Ayalon; Nikita Demidov; Vladimir Gordienko; Daniel Moreno; Nikita Belosludtcev; Sofya Savinova
- Web page: https://patentgrep.com/patent/US20250148674A1

## CPC

- H04L 51/10: Multimedia information
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06N 3/045: Combinations of networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06T 11/60: Creating or editing images; Combining images with text
- G06T 2200/24: involving graphical user interfaces [GUIs]
- H04L 51/52: for supporting social networking services
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Examples in the present disclosure relate to prompt-driven, conversation-specific image generation. A first user device of a first user of an interaction application transmits an image generation request. The interaction application enables the first user to interact with at least a second user. An image is automatically generated based on a prompt included in the image generation request, and the image is presented at the first user device. In response to receiving user input to select the image, the image is stored as a conversation-specific image in association with a first user profile of the first user and a second user profile of the second user. The conversation-specific image is presented at both the first user device of the first user and a second user device of the second user, together with conversation data associated with a conversation between the first user and the second user.

## Claims

### Claim 1

A system comprising:
at least one memory that stores instructions; and
one or more processors configured by the instructions to perform operations comprising:
receiving, from a first user device of a first user of an interaction application, an image generation request comprising a prompt, the interaction application enabling the first user to obtain automatically generated images and to interact with at least a second user, and the image generation request being associated with at least one conversation between the first user and the second user;
in response to receiving the image generation request, automatically generating, via a machine learning model, an image based on the prompt;
causing presentation of the image at the first user device;
receiving, from the first user device and via the interaction application, user input to select the image;
in response to receiving the user input to select the image, storing the image as a conversation-specific image in association with a first user profile of the first user and a second user profile of the second user; and
causing presentation of the conversation-specific image at both the first user device of the first user and a second user device of the second user, together with conversation data associated with the at least one conversation between the first user and the second user via the interaction application.

### Claim 2 (depends on 1)

The system of claim 1, wherein the user input to select the image is second user input, the operations comprising:
causing presentation of a user profile interface of the interaction application at the first user device, the user profile interface comprising a user-selectable image selection button;
receiving, from the first user device and via the interaction application, first user input to select the user-selectable image selection button; and
in response to receiving the first user input, causing presentation of an image selection interface at the first user device, the image selection interface enabling the first user to select the prompt to be applied for generating the conversation-specific image.

### Claim 3 (depends on 1)

The system of claim 1, wherein the user input to select the image is second user input, the operations comprising:
receiving, from the first user device and via the interaction application, first user input to modify the image generated via the machine learning model; and
in response to receiving the first user input, applying a digital effect to the image to generate a modified image, wherein the modified image is stored as the conversation-specific image.

### Claim 4 (depends on 3)

The system of claim 3, wherein the digital effect comprises a blurring effect.

### Claim 5 (depends on 1)

The system of claim 1, wherein the conversation-specific image comprises a wallpaper, the operations comprising:
in response to receiving the user input to select the image, causing presentation of a notification at the second user device, the notification indicating that the first user has changed the wallpaper associated with the at least one conversation.

### Claim 6 (depends on 1)

The system of claim 1, the operations comprising:
storing the first user profile, the second user profile, and relationship data for a relationship between the first user profile and the second user profile in a context of the interaction application; and
updating the relationship data to identify the conversation-specific image.

### Claim 7 (depends on 1)

The system of claim 1, wherein the conversation-specific image comprises a conversation-specific wallpaper, the operations comprising:
before the presentation of the conversation-specific wallpaper at the second user device, causing presentation, at both the first user device and the second user device, of a default wallpaper for the at least one conversation between the first user and the second user; and
after receiving the user input to select the image, replacing the default wallpaper with the conversation-specific wallpaper.

### Claim 8 (depends on 1)

The system of claim 1, wherein the prompt comprises a text prompt, the operations comprising:
causing presentation of a prompt selection interface of the interaction application at the first user device, the prompt selection interface comprising a text input section.

### Claim 9 (depends on 8)

The system of claim 8, wherein the prompt selection interface further comprises a set of user-selectable sample text prompts, and wherein user selection of a sample text prompt from the set of user-selectable sample text prompts causes presentation of the sample text prompt within the text input section.

### Claim 10 (depends on 8)

The system of claim 8, wherein the prompt selection interface further comprises a set of user-selectable sample text prompts, and wherein user selection of a sample text prompt from the set of user-selectable sample text prompts causes the sample text prompt to be automatically included in the image generation request.

### Claim 11 (depends on 8)

The system of claim 8, wherein the prompt selection interface further comprises an automatic prompt generation element, the automatic prompt generation element being user-selectable to cause automatic generation of a candidate text prompt.

### Claim 12 (depends on 11)

The system of claim 11, wherein the user input to select the image is second user input, the operations further comprising:
receiving, from the first user device, first user input to select the automatic prompt generation element;
in response to receiving the first user input, automatically generating the candidate text prompt; and
causing presentation of the candidate text prompt in the text input section.

### Claim 13 (depends on 1)

The system of claim 1, wherein the image generation request comprises an identifier of the second user or the second user profile.

### Claim 14 (depends on 1)

The system of claim 1, wherein the conversation-specific image comprises a conversation-specific wallpaper.

### Claim 15 (depends on 14)

The system of claim 14, wherein the conversation data is overlaid onto the conversation-specific wallpaper.

### Claim 16 (depends on 1)

The system of claim 1, wherein the prompt comprises a text prompt.

### Claim 17 (depends on 1)

The system of claim 1, wherein the machine learning model comprises a text-to-image machine learning model.

### Claim 18 (depends on 1)

The system of claim 1, wherein the machine learning model comprises at least one of a diffusion model, a Generative Adversarial Network (GAN), a Variational Autoencoder (VAE), or an autoregressive model.

### Claim 19

A method comprising:
receiving, from a first user device of a first user of an interaction application, an image generation request comprising a prompt, the interaction application enabling the first user to obtain automatically generated images and to interact with at least a second user, and the image generation request being associated with at least one conversation between the first user and the second user;
in response to receiving the image generation request, automatically generating, via a machine learning model, an image based on the prompt;
causing presentation of the image at the first user device;
receiving, from the first user device and via the interaction application, user input to select the image;
in response to receiving the user input to select the image, storing the image as a conversation-specific image in association with a first user profile of the first user and a second user profile of the second user; and
causing presentation of the conversation-specific image at both the first user device of the first user and a second user device of the second user, together with conversation data associated with the at least one conversation between the first user and the second user via the interaction application.

### Claim 20

One or more non-transitory computer-readable storage media, the one or more non-transitory computer-readable storage media including instructions that when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, from a first user device of a first user of an interaction application, an image generation request comprising a prompt, the interaction application enabling the first user to obtain automatically generated images and to interact with at least a second user, and the image generation request being associated with at least one conversation between the first user and the second user;
in response to receiving the image generation request, automatically generating, via a machine learning model, an image based on the prompt;
causing presentation of the image at the first user device;
receiving, from the first user device and via the interaction application, user input to select the image;
in response to receiving the user input to select the image, storing the image as a conversation-specific image in association with a first user profile of the first user and a second user profile of the second user; and
causing presentation of the conversation-specific image at both the first user device of the first user and a second user device of the second user, together with conversation data associated with the at least one conversation between the first user and the second user via the interaction application.
