PromptIQ: Who Cares About Prompts? Let System Handle It -- A Component-Aware Framework for T2I Generation

TL;DR

PromptIQ is an automated framework that refines prompts and evaluates image quality in text-to-image generation, addressing structural issues and reducing the need for manual prompt tuning.

Contribution

It introduces a novel Component-Aware Similarity metric and an iterative process for prompt refinement and quality assessment in T2I models.

Findings

Significantly improves image quality in T2I generation.

Enhances evaluation accuracy over existing metrics.

Reduces user effort in prompt engineering.

Abstract

Generating high-quality images without prompt engineering expertise remains a challenge for text-to-image (T2I) models, which often misinterpret poorly structured prompts, leading to distortions and misalignments. While humans easily recognize these flaws, metrics like CLIP fail to capture structural inconsistencies, exposing a key limitation in current evaluation methods. To address this, we introduce PromptIQ, an automated framework that refines prompts and assesses image quality using our novel Component-Aware Similarity (CAS) metric, which detects and penalizes structural errors. Unlike conventional methods, PromptIQ iteratively generates and evaluates images until the user is satisfied, eliminating trial-and-error prompt tuning. Our results show that PromptIQ significantly improves generation quality and evaluation accuracy, making T2I models more accessible for users with little to no prompt engineering expertise.