HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models

arXiv:2311.17528v2 Announce Type: replace
Abstract: Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will encounter unreasonable object duplication and exponentially increase the generation time. In this paper, we discover that object duplication arises from feature duplication in the deep blocks of the U-Net. Concurrently, We pinpoint the extended generation times to self-attention redundancy in U-Net's top blocks. To address these issues, we propose a tuning-free higher-resolution framework named …

abstract arxiv become creativity cs.cv diffusion diffusion models efficiency feature however image images object paper resolution synthesis type will