Preliminary Explorations with GPT-4o(mni) Native Image Generation

• URL: http://arxiv.org/abs/2505.05501v1
• Date: Tue, 06 May 2025 19:35:29 GMT
• Title: Preliminary Explorations with GPT-4o(mni) Native Image Generation
• Authors: Pu Cao, Feng Zhou, Junyi Ji, Qingye Kong, Zhixiang Lv, Mingjian Zhang, Xuekun Zhao, Siqi Wu, Yinghui Lin, Qing Song, Lu Yang,
• Abstract summary: Recently, the visual generation ability by GPT-4o(mni) has been unlocked by OpenAI.<n>In this paper, we aim to explore the capabilities of GPT-4o across various tasks.
• Score: 7.700772640399941
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Recently, the visual generation ability by GPT-4o(mni) has been unlocked by OpenAI. It demonstrates a very remarkable generation capability with excellent multimodal condition understanding and varied task instructions. In this paper, we aim to explore the capabilities of GPT-4o across various tasks. Inspired by previous study, we constructed a task taxonomy along with a carefully curated set of test samples to conduct a comprehensive qualitative test. Benefiting from GPT-4o's powerful multimodal comprehension, its image-generation process demonstrates abilities surpassing those of traditional image-generation tasks. Thus, regarding the dimensions of model capabilities, we evaluate its performance across six task categories: traditional image generation tasks, discriminative tasks, knowledge-based generation, commonsense-based generation, spatially-aware image generation, and temporally-aware image generation. These tasks not only assess the quality and conditional alignment of the model's outputs but also probe deeper into GPT-4o's understanding of real-world concepts. Our results reveal that GPT-4o performs impressively well in general-purpose synthesis tasks, showing strong capabilities in text-to-image generation, visual stylization, and low-level image processing. However, significant limitations remain in its ability to perform precise spatial reasoning, instruction-grounded generation, and consistent temporal prediction. Furthermore, when faced with knowledge-intensive or domain-specific scenarios, such as scientific illustrations or mathematical plots, the model often exhibits hallucinations, factual errors, or structural inconsistencies. These findings suggest that while GPT-4o marks a substantial advancement in unified multimodal generation, there is still a long way to go before it can be reliably applied to professional or safety-critical domains.

Related papers

• SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model [21.81341169834812]
  SridBench is the first benchmark for scientific figure generation.<n>It comprises 1,120 instances from leading scientific papers across 13 natural and computer science disciplines.<n>Results reveal that even top-tier models like GPT-4o-image lag behind human performance.
  arXiv  Detail & Related papers  (2025-05-28T08:51:01Z)
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset [140.1967962502411]
  We introduce a novel approach that employs a diffusion transformer to generate semantically rich CLIP image features.<n>A sequential pretraining strategy for unified models-first training on image understanding and subsequently on image generation offers practical advantages.<n>Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models.
  arXiv  Detail & Related papers  (2025-05-14T17:11:07Z)
• A Preliminary Study for GPT-4o on Image Restoration [7.784948465884567]
  OpenAI's GPT-4o model has demonstrated unprecedented performance in image generation.<n>We present the first systematic evaluation of GPT-4o across diverse restoration tasks.
  arXiv  Detail & Related papers  (2025-05-08T20:00:11Z)
• Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability [6.586119023242877]
  OpenAI's multimodal GPT-4o has demonstrated remarkable capabilities in image generation and editing.<n>But its ability to achieve world knowledge-informed semantic synthesis remains unproven.<n>Our study calls for the development of more robust benchmarks and training strategies.
  arXiv  Detail & Related papers  (2025-04-09T16:10:15Z)
• An Empirical Study of GPT-4o Image Generation Capabilities [40.86026243294732]
  We conduct an empirical study of GPT-4o's image generation capabilities, benchmarking it against leading open-source and commercial models.<n>Our analysis highlights the strengths and limitations of GPT-4o under various settings, and situates it within the broader evolution of generative modeling.
  arXiv  Detail & Related papers  (2025-04-08T12:34:36Z)
• GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation [28.235805447825896]
  OpenAI's GPT4o model has demonstrated surprisingly good capabilities in image generation and editing.<n>This report presents the first-look evaluation benchmark (named GPT-ImgEval)<n>We show GPT-4o's performance across three critical dimensions: generation quality, (2) editing proficiency, and (3) world knowledge-informed synthesis.
  arXiv  Detail & Related papers  (2025-04-03T17:23:16Z)
• Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining [49.04935506942202]
  Lumina-mGPT is a family of multimodal autoregressive models capable of various vision and language tasks.<n>By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models.
  arXiv  Detail & Related papers  (2024-08-05T17:46:53Z)
• GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition? [82.40761196684524]
  This paper centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks. We conduct extensive experiments to evaluate GPT-4's performance across images, videos, and point clouds. Our findings show that GPT-4, enhanced with rich linguistic descriptions, significantly improves zero-shot recognition.
  arXiv  Detail & Related papers  (2023-11-27T11:29:10Z)
• A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering [53.70661720114377]
  multimodal large models (MLMs) have significantly advanced the field of visual understanding, offering remarkable capabilities in realm of visual question answering (VQA) Yet, the true challenge lies in the domain of knowledge-intensive VQA tasks, which necessitate deep comprehension of the visual information in conjunction with a vast repository of learned knowledge. To uncover such capabilities, we provide an in-depth evaluation from three perspectives: 1) Commonsense Knowledge, which assesses how well models can understand visual cues and connect to general knowledge; 2) Fine-grained World Knowledge, which tests the model's skill in reasoning out specific knowledge from images, showcasing
  arXiv  Detail & Related papers  (2023-11-13T18:22:32Z)
• GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks [70.98062518872999]
  We validate GPT-4V's capabilities for evaluation purposes, addressing tasks ranging from foundational image-to-text and text-to-image synthesis to high-level image-to-image translations and multi-images to text alignment. Notably, GPT-4V shows promising agreement with humans across various tasks and evaluation methods, demonstrating immense potential for multi-modal LLMs as evaluators.
  arXiv  Detail & Related papers  (2023-11-02T16:11:09Z)
• The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) [121.42924593374127]
  We analyze the latest model, GPT-4V, to deepen the understanding of LMMs. GPT-4V's unprecedented ability in processing arbitrarily interleaved multimodal inputs makes it a powerful multimodal generalist system. GPT-4V's unique capability of understanding visual markers drawn on input images can give rise to new human-computer interaction methods.
  arXiv  Detail & Related papers  (2023-09-29T17:34:51Z)
• Sparks of Artificial General Intelligence: Early experiments with GPT-4 [66.1188263570629]
  GPT-4, developed by OpenAI, was trained using an unprecedented scale of compute and data. We demonstrate that GPT-4 can solve novel and difficult tasks that span mathematics, coding, vision, medicine, law, psychology and more. We believe GPT-4 could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system.
  arXiv  Detail & Related papers  (2023-03-22T16:51:28Z)
• Generative Hierarchical Features from Synthesizing Images [65.66756821069124]
  We show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks.
  arXiv  Detail & Related papers  (2020-07-20T18:04:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.