Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning

TL;DR

Fine-T2I introduces a large, high-quality, open dataset with over 6 million text-image pairs, combining synthetic and real images, to significantly improve text-to-image model fine-tuning across diverse tasks and styles.

Contribution

The paper presents Fine-T2I, a comprehensive, rigorously filtered dataset that addresses the scarcity of high-quality open datasets for T2I fine-tuning, enabling better model performance.

Findings

Fine-T2I improves generation quality across models.

Fine-T2I enhances instruction adherence.

Dataset covers diverse tasks and styles.

Abstract

High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution, poor text-image alignment, or limited diversity, resulting in a clear performance gap between open research models and enterprise-grade models. In this work, we present Fine-T2I, a large-scale, high-quality, and fully open dataset for T2I fine-tuning. Fine-T2I spans 10 task combinations, 32 prompt categories, 11 visual styles, and 5 prompt templates, and combines synthetic images generated by strong modern models with carefully curated real images from professional photographers. All samples are rigorously filtered for text-image alignment, visual fidelity, and prompt quality, with over 95% of initial candidates removed. The final dataset contains over 6 million text-image pairs, around 2 TB on disk, approaching the scale of pretraining datasets while maintaining fine-tuning-level quality. Across a diverse set of pretrained diffusion and autoregressive models, fine-tuning on Fine-T2I consistently improves both generation quality and instruction adherence, as validated by human evaluation, visual comparison, and automatic metrics. We release Fine-T2I under an open license to help close the data gap in T2I fine-tuning in the open community.