PromptIQ: Who Cares About Prompts? Let System Handle It -- A Component-Aware Framework for T2I Generation
This makes text-to-image models more accessible for users with little to no prompt engineering expertise, though it appears incremental in addressing known bottlenecks.
The paper tackles the challenge of generating high-quality images without prompt engineering expertise in text-to-image models by introducing PromptIQ, an automated framework that refines prompts and assesses image quality using a novel Component-Aware Similarity metric. Results show it significantly improves generation quality and evaluation accuracy.
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.