Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it remains unclear whether these models can accurately represent a wide variety of realistic visual entities. To bridge this gap, we propose KITTEN, a benchmark for Knowledge-InTensive image generaTion on real-world ENtities. Using KITTEN, we conduct a systematic study of the latest text-to-image models and retrieval-augmented models, focusing on their ability to generate real-world visual entities, such as landmarks and animals. Analysis using carefully designed human evaluations, automatic metrics, and MLLM evaluations show that even advanced text-to-image models fail to generate accurate visual details of entities. While retrieval-augmented models improve entity fidelity by incorporating reference images, they tend to over-rely on them and struggle to create novel configurations of the entity in creative text prompts.
@article{arxiv.2410.11824,
title = {KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities},
author = {Hsin-Ping Huang and Xinyi Wang and Yonatan Bitton and Hagai Taitelbaum and Gaurav Singh Tomar and Ming-Wei Chang and Xuhui Jia and Kelvin C. K. Chan and Hexiang Hu and Yu-Chuan Su and Ming-Hsuan Yang},
journal= {arXiv preprint arXiv:2410.11824},
year = {2025}
}