# An Empirical Study of GPT-4o Image Generation Capabilities

arXiv: https://arxiv.org/abs/2504.05979 · HTML: https://mlsanity.com/paper/2504.05979/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- First posted on arXiv 8 Apr 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Built on by (most cited first, 26 of 26)

- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation](https://mlsanity.com/paper/2506.18095/) (2025)
- [Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model](https://mlsanity.com/paper/2505.23606/) (2025)
- [TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation](https://mlsanity.com/paper/2505.05422/) (2025)
- [JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent](https://mlsanity.com/paper/2506.17612/) (2025)
- [How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks](https://mlsanity.com/paper/2507.01955/) (2025)
- [DanceOPD: On-Policy Generative Field Distillation](https://mlsanity.com/paper/2606.27377/) (2026)
- [EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing](https://mlsanity.com/paper/2512.11715/) (2025)
- [HERO: Hierarchical Extrapolation and Refresh for Efficient World Models](https://mlsanity.com/paper/2508.17588/) (2025)
- [MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation](https://mlsanity.com/paper/2505.21483/) (2025)
- [SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency](https://mlsanity.com/paper/2510.22994/) (2025)
- [ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks](https://mlsanity.com/paper/2603.27862/) (2026)
- [STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning](https://mlsanity.com/paper/2512.13752/) (2025)
- [InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation](https://mlsanity.com/paper/2603.05898/) (2026)
- [HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images](https://mlsanity.com/paper/2603.02210/) (2026)
- [Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners](https://mlsanity.com/paper/2605.14709/) (2026)
- [MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks](https://mlsanity.com/paper/2509.14638/) (2025)
- [FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models](https://mlsanity.com/paper/2510.02133/) (2025)
- [Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start](https://mlsanity.com/paper/2511.05095/) (2025)
- [TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark](https://mlsanity.com/paper/2603.28613/) (2026)
- [AI-generated Images Challenge Visual Trust in High-risk Scenarios](https://mlsanity.com/paper/2607.22745/) (2026)
- [Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling](https://mlsanity.com/paper/2506.19391/) (2025)
- [Chain of Time: In-Context Physical Simulation with Image Generation Models](https://mlsanity.com/paper/2511.00110/) (2025)
- [Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks](https://mlsanity.com/paper/2606.18354/) (2026)
- [ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation](https://mlsanity.com/paper/2609.15100/) (2026)
- [ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing](https://mlsanity.com/paper/2609.38541/) (2026)

## Abstract (arXiv)

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: hrefhttps://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Genhttps://github.com/Ephemeral182/Empirical-Study-of-GPT-4o-Image-Gen.