AI Image Generation via Keyword Character Set Editing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current drawing software or image generators require users to input textual descriptions and instruction sets to generate desired images, which can be cumbersome, especially for users unfamiliar with these instructions.

Innovation Solution

A method that generates an artificial intelligence image by receiving input images, creating a keyword character set using an image description model, performing string editing operations based on editing requests, and generating an artificial intelligence image using an image generation model, without the need for users to input additional instruction sets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users input textual descriptions and instruction sets to generate images, then image generation capability is achieved, but operation complexity and user threshold increase

Engineering Contradiction:

Improveimage generation operationVSAvoidinstruction set input requirement

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically generates keyword character sets from input images using image description models, eliminating the need for users to manually input instruction sets. The system serves itself by extracting necessary textual information directly from the visual content, making the operation self-contained and user-friendly.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual text input with an automated image recognition and description generation system. The image description model automatically converts visual information into actionable keyword character sets, substituting manual operation with intelligent automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If users familiar with instruction sets generate images, then precise control is achieved, but accessibility for unfamiliar users decreases

Engineering Contradiction:

Improveuser accessibilityVSAvoidinstruction set knowledge requirement

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The image description model acts as an intermediary between the input image and the image generation model. It automatically generates the keyword character sets that would otherwise require user knowledge to input, bridging the gap between visual input and actionable instructions without requiring user expertise.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system generates its own instruction sets by automatically describing the input images. This self-service capability eliminates the need for users to possess specialized knowledge of instruction sets, making the technology accessible to a broader audience while maintaining precise control over the generation process.

Inventive Principle:

Principle #25Self-service

3Productivity

If manual instruction set input is required, then generation precision is maintained, but operation time and complexity increase

Engineering Contradiction:

Improveimage generation speedVSAvoidinstruction set input time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary action by automatically generating keyword character sets from input images before the actual image generation process. This pre-processing step eliminates the need for users to spend time crafting instruction sets, significantly reducing operation time while maintaining generation precision through the automated description quality.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent substitutes the manual time-consuming process of instruction set input with automated image description generation. The image description model rapidly converts visual information into actionable keywords, dramatically increasing productivity by eliminating the time bottleneck associated with manual text input while preserving generation accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4492329A1Method, computer device, non-transitory computer-readable recording medium, and computer program product for generating image

Publication Date: 2025.01.15 EVOLUTIVE LABS CO LTD

Figure 1
Figure 2
Figure 3

AI summary

A method for generating an image suitable for generating an artificial intelligence image (540, 840, 940) by means of a computer device (200) comprises receiving at least one input image (510), generating a keyword character set (520) based on the at least one input image (510), performing at least one string editing operation on the keyword character set (520) based on an editing instruction set corresponding to an editing request after receiving the editing request from any one of at least one editing button (630), generating an editing character set (530, 830, 930), and generating the artificial intelligence image (540, 840, 940) based on the editing character set (530, 830, 930). Thus, the method is suitable for generating an artificial intelligence image (540, 840, 940) and solves the issue that it is necessary for a user to first input a corresponding instruction set before a user-desired image can be generated.