发表机构
Lancaster University; South China University of Technology; NVIDIA AI Tech Centre（兰卡斯特大学; 华南理工大学; 英伟达AI技术中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对现成DiT模型适配高分辨率图像合成的空间紊乱、生成时间长两大挑战，提出新方法，经实验验证其有效性，代码公开。
AI 中文摘要
无需训练的文本到高分辨率图像生成近期受到越来越多的研究关注。然而，现有针对该任务的研究主要聚焦于将现成的基于U-Net的扩散模型适配至高分辨率，尽管现成的扩散Transformer（DiT）模型在有限分辨率下具备强大的文本到图像生成能力，但在适配该类模型方面进展有限。本研究发现，阻碍现成DiT模型以无需训练方式应用于高分辨率图像合成的两大关键挑战，即空间紊乱与生成时间过长。为应对这些挑战，我们提出了一种专门适配现成DiT模型用于高分辨率图像合成的新方法。大量实验验证了该方法的有效性，代码可在指定链接获取。
英文摘要
Training-free text-to-high-resolution image generation has recently attracted growing research attention. However, existing studies on this task primarily focus on adapting off-the-shelf U-Net-based diffusion models to high resolutions, with limited progress on adapting off-the-shelf Diffusion Transformer (DiT) models despite their strong text-to-image generation capabilities at limited resolutions. In this work, we find two key challenges particularly hindering the application of off-the-shelf DiT models for high-resolution image synthesis in a training-free manner, namely, spatial disorder and long generation time. To address these challenges, we propose a novel method tailored to adapt off-the-shelf DiT models for high-resolution image synthesis. Extensive experiments show the efficacy of our method. Our code is available at: https://github.com/zylwithxy/HRDiT.
CommentsAccepted by ECCV 2026
