Text-to-Design Template Generation With Intent-Based Asset Alignment

Solution Overview

Problem

Conventional methods for generating design documents are time-consuming and require significant manual editing, often failing to fully embody the creator's intent due to template constraints, leading to unsatisfactory results.

Innovation Solution

A design generation system that encodes user prompts to generate intent embeddings, retrieves and filters design templates based on these embeddings, and integrates image and text assets automatically, ensuring compatibility and aesthetic harmony.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual template modification is used, then design customization is possible, but time consumption increases and skill requirements rise

Engineering Contradiction:

Improvedesign customizationVSAvoidtime consumption

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically selecting and modifying templates based on text prompts without requiring user manual intervention. The AI model processes the text prompt, retrieves relevant templates, and applies appropriate modifications autonomously, eliminating the need for users to manually edit templates while maintaining design customization capabilities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual editing process with an AI-based automated system. Instead of users manually modifying templates through traditional interface operations, the system uses natural language processing and AI models to automatically generate and apply template modifications based on text prompts, substituting manual mechanical operations with intelligent automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If manual template modification is used, then design customization is possible, but skill requirements increase

Engineering Contradiction:

Improvedesign customizationVSAvoidskill requirements

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically selecting and modifying templates based on text prompts without requiring user manual intervention. The AI model processes the text prompt, retrieves relevant templates, and applies appropriate modifications autonomously, eliminating the need for users to manually edit templates while maintaining design customization capabilities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual editing process with an AI-based automated system. Instead of users manually modifying templates through traditional interface operations, the system uses natural language processing and AI models to automatically generate and apply template modifications based on text prompts, substituting manual mechanical operations with intelligent automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Stability of the object's composition

If template constraints are followed, then template consistency is maintained, but design intent accuracy decreases

Engineering Contradiction:

Improvetemplate consistencyVSAvoiddesign intent accuracy

Core Design Contradiction:

Stability of the object's compositionVSManufacturing precision

Solution Approach 1:

The system applies dynamic modifications to templates based on the specific text prompt and design intent. Rather than using static, fixed templates, the AI model dynamically adjusts and modifies template elements such as image placement, text positioning, and layout configuration to accurately reflect the user's intended message while maintaining the underlying template structure and consistency.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12493739B2Generating full designs from text

Publication Date: 2025.12.09 ADOBE INC

AI summary

Systems and methods for generating full designs from text include retrieving a plurality of document templates based on a design prompt, and filtering the document templates based on an image prompt. A document template is then selected based on the filtering, and a document is generated based on the document template and the image prompt. Embodiments are further configured to generate content from one or more of the prompts, where the content is included in the final design document.