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.

以简单、快速的扩散外推过程为目标，我们提出了无需调优的 CutDiffusion 方法，通过修剪标准的扩散过程，将其划分为综合结构去噪的初始阶段和专注于具体细节修饰的后续阶段，从而提高了扩散适应性，同时降低时间和成本开销。