Abstract
Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by sharpening attention distributions, but fail to preserve fine-grained semantic details and introduce obvious artifacts. In this work, we analyze the characteristics of DiTs and propose TIDE, a training-free text-to-image (T2I) extrapolation method that enables generation with arbitrary resolution and aspect ratio without additional sampling overhead. We identify the core factor for prompt information loss, and introduce a text anchoring mechanism to correct the imbalance between text and image tokens. To further eliminate artifacts, we design a dynamic temperature control mechanism that leverages the pattern of spectral progression in the diffusion process. Extensive evaluations demonstrate that TIDE delivers high-quality resolution extrapolation capability and integrates seamlessly with existing state-of-the-art methods.
Abstract (translated)
扩散变压器（Diffusion Transformer，DiT）在生成高于训练分辨率的图像时面临挑战，尤其是在结构退化方面，这是由于注意力稀释导致的。先前的方法试图通过锐化注意力分布来缓解这一问题，但未能保留细微的语义细节，并引入了明显的伪影。在这项工作中，我们分析了DiTs的特点，并提出了TIDE（Training-free Image DEextrapolation），这是一种无需额外训练即可实现任意分辨率和长宽比生成的文字到图像（Text-to-Image, T2I）外推方法。我们确定了提示信息丢失的核心因素，并引入了一种文本锚定机制来纠正文字与图像标记之间的不平衡。为了进一步消除伪影，我们设计了一个动态温度控制机制，利用扩散过程中的频谱进展模式。 广泛评估表明，TIDE具有高质量的分辨率外推能力，并且能够无缝集成到现有的最先进的方法中。
URL
https://arxiv.org/abs/2603.08928
