让扩散模型生成超高清图像，解决内容重复和画质下降问题
UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers
- 通过修正位置编码的主频周期，防止生成时内容重复
- 用熵引导注意力集中，提升细节清晰度同时保持结构一致
- 可直接生成6K×6K图像，无需低分辨率引导，适合高分辨率生成任务
近期的图像扩散变换器虽能生成高保真图像，但在超大尺寸生成时面临内容重复与画质下降的问题。本文提出UltraImage，从频率层面分析位置编码，发现重复源于主导频率的周期性，其周期与训练分辨率对齐。为此引入递归主导频率校正，将该频率限制在单个周期内以实现外推。同时，发现画质下降源于注意力稀释，提出熵引导的自适应注意力聚焦机制，对局部细节赋予更高关注因子，对全局模式降低关注，以保持结构一致性。实验表明，UltraImage在Qwen-Image和Flux（约4K）上均优于现有方法，显著减少重复并提升视觉质量。更重要的是，其可直接从1328p训练分辨率生成6K×6K图像，无需低分辨率引导，展现强大极端外推能力。
原文摘要 · Abstract (English)
Recent image diffusion transformers achieve high-fidelity generation, but struggle to generate images beyond these scales, suffering from content repetition and quality degradation. In this work, we present UltraImage, a principled framework that addresses both issues. Through frequency-wise analysis of positional embeddings, we identify that repetition arises from the periodicity of the dominant frequency, whose period aligns with the training resolution. We introduce a recursive dominant frequency correction to constrain it within a single period after extrapolation. Furthermore, we find that quality degradation stems from diluted attention and thus propose entropy-guided adaptive attention concentration, which assigns higher focus factors to sharpen local attention for fine detail and lower ones to global attention patterns to preserve structural consistency. Experiments show that UltraImage consistently outperforms prior methods on Qwen-Image and Flux (around 4K) across three generation scenarios, reducing repetition and improving visual fidelity. Moreover, UltraImage can generate images up to 6K*6K without low-resolution guidance from a training resolution of 1328p, demonstrating its extreme extrapolation capability. Project page is available at \href{https://thu-ml.github.io/ultraimage.github.io/}{https://thu-ml.github.io/ultraimage.github.io/}.
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。