CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method

arXiv:2404.15141v1 Announce Type: new
Abstract: 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 …

abstract adaptability arxiv cs.ai cs.cv diffusion diffusion models free improving low making performance process resolution simple simplifying type wise