Score: 1

ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization

Published: July 4, 2025 | arXiv ID: 2507.03275v1

By: Haosheng Gan , Berk Tinaz , Mohammad Shahab Sepehri and more

Potential Business Impact:

Makes AI better at drawing what you imagine.

Business Areas:
Visual Search Internet Services

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We introduce ConceptMix++, a framework that disentangles prompt phrasing from visual generation capabilities by applying iterative prompt optimization. Building on ConceptMix, our approach incorporates a multimodal optimization pipeline that leverages vision-language model feedback to refine prompts systematically. Through extensive experiments across multiple diffusion models, we show that optimized prompts significantly improve compositional generation performance, revealing previously hidden model capabilities and enabling fairer comparisons across T2I models. Our analysis reveals that certain visual concepts -- such as spatial relationships and shapes -- benefit more from optimization than others, suggesting that existing benchmarks systematically underestimate model performance in these categories. Additionally, we find strong cross-model transferability of optimized prompts, indicating shared preferences for effective prompt phrasing across models. These findings demonstrate that rigid benchmarking approaches may significantly underrepresent true model capabilities, while our framework provides more accurate assessment and insights for future development.

Country of Origin
🇺🇸 United States

Page Count
22 pages

Category
Computer Science:
CV and Pattern Recognition