Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

TL;DR

This paper introduces Echo-4o, a synthetic image dataset generated by GPT-4o, which enhances open-source image generation models by addressing rare scenarios and providing clean supervision, leading to improved performance and new evaluation benchmarks.

Contribution

The paper presents Echo-4o-Image, a large synthetic dataset for fine-tuning multimodal models, and introduces new benchmarks for evaluating complex and imaginative image generation tasks.

Findings

Echo-4o-Image improves model performance on standard benchmarks.

Synthetic data addresses rare and complex scenarios effectively.

Transferability of Echo-4o-Image benefits multiple foundation models.

Abstract

Recently, GPT-4o has garnered significant attention for its strong performance in image generation, yet open-source models still lag behind. Several studies have explored distilling image data from GPT-4o to enhance open-source models, achieving notable progress. However, a key question remains: given that real-world image datasets already constitute a natural source of high-quality data, why should we use GPT-4o-generated synthetic data? In this work, we identify two key advantages of synthetic images. First, they can complement rare scenarios in real-world datasets, such as surreal fantasy or multi-reference image generation, which frequently occur in user queries. Second, they provide clean and controllable supervision. Real-world data often contains complex background noise and inherent misalignment between text descriptions and image content, whereas synthetic images offer pure backgrounds and long-tailed supervision signals, facilitating more accurate text-to-image alignment. Building on these insights, we introduce Echo-4o-Image, a 180K-scale synthetic dataset generated by GPT-4o, harnessing the power of synthetic image data to address blind spots in real-world coverage. Using this dataset, we fine-tune the unified multimodal generation baseline Bagel to obtain Echo-4o. In addition, we propose two new evaluation benchmarks for a more accurate and challenging assessment of image generation capabilities: GenEval++, which increases instruction complexity to mitigate score saturation, and Imagine-Bench, which focuses on evaluating both the understanding and generation of imaginative content. Echo-4o demonstrates strong performance across standard benchmarks. Moreover, applying Echo-4o-Image to other foundation models (e.g., OmniGen2, BLIP3-o) yields consistent performance gains across multiple metrics, highlighting the datasets strong transferability.