Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05979 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913788345712640 |
|---|---|
| author | Chen, Sixiang Bai, Jinbin Zhao, Zhuoran Ye, Tian Shi, Qingyu Zhou, Donghao Chai, Wenhao Lin, Xin Wu, Jianzong Tang, Chao Xu, Shilin Zhang, Tao Yuan, Haobo Zhou, Yikang Chow, Wei Li, Linfeng Li, Xiangtai Zhu, Lei Qi, Lu |
| author_facet | Chen, Sixiang Bai, Jinbin Zhao, Zhuoran Ye, Tian Shi, Qingyu Zhou, Donghao Chai, Wenhao Lin, Xin Wu, Jianzong Tang, Chao Xu, Shilin Zhang, Tao Yuan, Haobo Zhou, Yikang Chow, Wei Li, Linfeng Li, Xiangtai Zhu, Lei Qi, Lu |
| contents | 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demonstrated the feasibility of high-fidelity multimodal generation, their architectural design remains mysterious and unpublished.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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05979 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Empirical Study of GPT-4o Image Generation Capabilities Chen, Sixiang Bai, Jinbin Zhao, Zhuoran Ye, Tian Shi, Qingyu Zhou, Donghao Chai, Wenhao Lin, Xin Wu, Jianzong Tang, Chao Xu, Shilin Zhang, Tao Yuan, Haobo Zhou, Yikang Chow, Wei Li, Linfeng Li, Xiangtai Zhu, Lei Qi, Lu Computer Vision and Pattern Recognition 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}. |
| title | An Empirical Study of GPT-4o Image Generation Capabilities |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05979 |