Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency texture details. We introduce VINS-120K, the first large-scale dataset for instruction-based UHR image editing, comprising 120K carefully curated triplets of instruction, input image, and edited image. Each image exceeds 4K resolution (≥4096 × 4096) and is filtered through a rigorous multi-stage pipeline to ensure visual quality, instruction alignment, and aesthetic fidelity. Built on VINS-120K, we further develop a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime. We also present VINS-4KEval, a benchmark covering diverse editing types, to facilitate consistent evaluation in UHR settings. Experiments confirm that our work improves fine-grained detail synthesis and texture realism in UHR image editing.
@article{arxiv.2605.23518,
title = {VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset},
author = {Zhizhou Chen and Shanyan Guan and Zhanxin Gao and En Ci and Yanhao Ge and Wei Li and Zhenyu Zhang and Jian Yang and Ying Tai},
journal= {arXiv preprint arXiv:2605.23518},
year = {2026}
}