Prompt Merging and Image Retrieval for Faster AI Content Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AI-generated content creation methods, particularly in text-to-image models, require numerous iterations and substantial computing resources to produce desired images, leading to inefficiency and resource wastage.

Innovation Solution

A system that analyzes input prompts, suggests updated parameters, merges prompts, and searches a database of previously generated images to quickly produce desired content by leveraging a prompt analysis and merge engine, image search engine, and classifiers to streamline the process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional text-to-image models are used to generate images from prompts, then image generation capability is achieved, but the process requires numerous iterations and substantial computing resources

Engineering Contradiction:
Improveimage generation speedVSAvoidcomputing resource consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by analyzing the input prompt beforehand to extract key entities, attributes, and relationships. This preliminary analysis creates a structured representation that guides the image generation process, reducing the need for multiple iterative attempts and thereby decreasing computing resource consumption while maintaining productivity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary component that acts as a bridge between the text prompt and the image generation model. This intermediary processes the prompt to extract semantic information and transforms it into a format that directly guides image generation, eliminating the need for numerous trial-and-error iterations and reducing computational overhead

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If multiple iterations are performed to achieve desired image quality, then image accuracy improves, but time consumption increases

Engineering Contradiction:
Improveimage quality accuracyVSAvoidgeneration time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of the prompt to pre-determine key image characteristics and generation parameters before the actual image generation occurs. This preliminary action ensures that the first generation attempt is highly accurate, eliminating the need for time-consuming iterative refinements while maintaining high image quality

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where the system analyzes the relationship between prompts and generated images to learn and improve. By incorporating feedback from prompt analysis and image evaluation, the system optimizes generation parameters in advance, achieving high accuracy in fewer iterations and reducing overall generation time

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS12566914B2System and methods to facilitate content generation using generative artificial intelligence models
Publication Date: 2026.03.03 ADEIA IMAGING LLC
  • US12566914B2 patent drawing
  • US12566914B2 patent drawing
  • US12566914B2 patent drawing

AI summary

The present disclosure is directed to systems and methods to enhance the process of creating an artificial intelligence (AI) generated content or content items, such as images, text, video, sounds, etc., using a text or other suitable prompt, such as via voice input. The systems and methods disclosed provide streamlined content generation with, e.g., reduced processing power and computing time. In an embodiment the systems and methods receive a prompt for generating a first content item using a generative artificial intelligence (AI) model and retrieve, based on the prompt, a collection of matching content items. The systems and methods may then receive input selecting one of the content items from the collection and identify a prompt used to generate the selected content item. The systems and methods may then merge using a trained natural language processing model, the received prompt with the prompt of the selected content item to create a third prompt. In an embodiment the systems and methods may modify the third prompt based on additional input and, based on the modified third prompt, generate a second content item.