AI Design Generation Pipeline Resolving Template Limitations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing productivity applications, such as graphic design and presentation tools, face limitations in generating design suggestions due to the limited size of their template catalogs, which restricts their ability to present designs that fully satisfy user preferences.
Innovation Solution
The system employs a chain-of-models approach leveraging generative AI and Deep Learning models. It receives textual user input, uses a Large Language Model (LLM) to restructure the input, and then generates a prompt for a text-to-image model to produce a proposed design. Additionally, it submits the design to a text placement model to determine the optimal placement and styling of text within the design.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a template-based design system is used, then the system structure is simple and easy to implement, but the number of available design options is limited
Solution Approach 1:
The patent replaces the traditional mechanical template-based design system with an AI-generated design system. Instead of selecting from predefined templates, the system uses generative AI models to create unique design options based on user inputs, thereby increasing design versatility while managing system complexity through automated generation rather than manual curation of numerous templates
Solution Approach 2:
The system changes the fundamental parameter of design generation from static template selection to dynamic AI generation. By using prompts and generative models, the system can create unlimited design variations based on changing parameters and user requirements, transforming the limited template catalog into an infinite design possibilities system
2Adaptability or versatility
If the template catalog is expanded to provide more design options, then user preference satisfaction improves, but the system complexity and data management burden increase
Solution Approach 1:
The system employs AI models to autonomously generate design options without requiring manual creation and maintenance of extensive template catalogs. The generative AI self-services by creating unique designs based on prompts, eliminating the need for users or administrators to manage large collections of templates while still providing diverse design options
3Adaptability or versatility
If AI generative models are used to create designs from prompts, then the number of possible designs becomes virtually limitless, but the computational resources and processing time required increase
Solution Approach 1:
The system performs preliminary actions by using smaller language models to process user prompts and generate design concepts before engaging the more resource-intensive image generation models. This staged approach breaks down the computational task into smaller steps, reducing overall resource consumption while still achieving high-quality design generation from prompts
Data Source
AI summary
A device includes a processor, and a memory storing executable instructions which, when executed by the processor, cause the processor alone or in combination with other processors to perform the following functions: receive textual user input from a user describing a design to be generated; implement a first prompt generator to generate a first prompt for a Large Language Model (LLM) to restructure the user input; and implement a second prompt generator to generate a second prompt for a text-to-image model using output of the LLM to produce, the second prompt to prompt the text-to-image model to produce a proposed design based on the user input. The proposed design is provided to the user via an application comprising controls for further editing the proposed design.