Search papers, labs, and topics across Lattice.
The authors introduce Fine-T2I, a large-scale (6M image-text pairs, 2TB), high-quality, and openly licensed dataset for text-to-image fine-tuning, addressing limitations in existing datasets regarding resolution, alignment, and diversity. Fine-T2I combines synthetically generated images with curated real images, rigorously filtered for quality. Fine-tuning various pretrained diffusion and autoregressive models on Fine-T2I demonstrates consistent improvements in generation quality and instruction adherence, as validated through human evaluation and automatic metrics.
Bridging the gap between open-source and enterprise T2I models, Fine-T2I offers a massive, meticulously curated dataset that unlocks significant gains in generation quality and instruction following through fine-tuning.
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.
