The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks. Recent advances, especially the GPT-4o, have demonstrated the feasibility of high-fidelity multimodal generation, their architectural design remains mysterious and unpublished. This prompts the question of whether image and text generation have already been successfully integrated into a unified framework for those methods. In this work, we conduct an empirical study of GPT-4o's image generation capabilities, benchmarking it against leading open-source and commercial models. Our evaluation covers four main categories, including text-to-image, image-to-image, image-to-3D, and image-to-X generation, with more than 20 tasks. Our analysis highlights the strengths and limitations of GPT-4o under various settings, and situates it within the broader evolution of generative modeling. Through this investigation, we identify promising directions for future unified generative models, emphasizing the role of architectural design and data scaling. For a high-definition version of the PDF, please refer to the link on GitHub: \href{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}{https://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen}.
@article{arxiv.2504.05979,
title = {An Empirical Study of GPT-4o Image Generation Capabilities},
author = {Sixiang Chen and Jinbin Bai and Zhuoran Zhao and Tian Ye and Qingyu Shi and Donghao Zhou and Wenhao Chai and Xin Lin and Jianzong Wu and Chao Tang and Shilin Xu and Tao Zhang and Haobo Yuan and Yikang Zhou and Wei Chow and Linfeng Li and Xiangtai Li and Lei Zhu and Lu Qi},
journal= {arXiv preprint arXiv:2504.05979},
year = {2025}
}