Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i.e., diffusion extrapolation, significantly improves diffusion adaptability. We propose tuning-free CutDiffusion, aimed at simplifying and accelerating the diffusion extrapolation process, making it more affordable and improving performance. CutDiffusion abides by the existing patch-wise extrapolation but cuts a standard patch diffusion process into an initial phase focused on comprehensive structure denoising and a subsequent phase dedicated to specific detail refinement. Comprehensive experiments highlight the numerous almighty advantages of CutDiffusion: (1) simple method construction that enables a concise higher-resolution diffusion process without third-party engagement; (2) fast inference speed achieved through a single-step higher-resolution diffusion process, and fewer inference patches required; (3) cheap GPU cost resulting from patch-wise inference and fewer patches during the comprehensive structure denoising; (4) strong generation performance, stemming from the emphasis on specific detail refinement.

中文翻译：

---

CutDiffusion：一种简单、快速、廉价且强的扩散外推方法

转换大型预训练的低分辨率扩散模型以满足更高分辨率的需求，即扩散外推，显着提高了扩散适应性。我们提出免调整的 CutDiffusion，旨在简化和加速扩散外推过程，使其更加经济实惠并提高性能。 CutDiffusion 遵循现有的逐块外推法，但将标准的块扩散过程切割为专注于全面结构去噪的初始阶段和致力于特定细节细化的后续阶段。综合实验凸显了CutDiffusion的众多强大优势：（1）简单的方法构建，无需第三方参与即可实现简洁的高分辨率扩散过程； （2）通过单步高分辨率扩散过程实现快速推理速度，并且需要更少的推理补丁； （3）在综合结构去噪过程中，由于分片推理和更少的分片，GPU成本低廉； (4)强大的生成性能，源于对具体细节细化的重视。