无需训练，让现成DiT模型生成高清图像。
HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
- 设计新方法解决DiT生成高清图的布局混乱与速度慢问题
- 在不微调模型前提下实现1024×1024分辨率图像生成
- 适合希望快速部署高分辨率生成模型的研究者
无需训练的文本到高分辨率图像生成近期受到广泛关注。然而，现有研究主要集中在适配现成的基于U-Net的扩散模型至高分辨率，对具备较强文本到图像生成能力但仅限于低分辨率的现成扩散Transformer（DiT）模型的适配进展有限。本文发现两个关键挑战：空间布局紊乱和生成时间过长。为此，我们提出一种专为适配现成DiT模型而设计的新方法，以实现训练自由的高分辨率图像合成。大量实验验证了该方法的有效性。代码已公开于：https://github.com/zylwithxy/HRDiT。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。