LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights

arXiv:2404.11936v1 Announce Type: new
Abstract: Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDMs on resource-limited devices remains a complex issue, presenting challenges such as memory consumption and inference speed. To address this issue, we introduce LD-Pruner, a novel performance-preserving structured pruning method for compressing LDMs. Traditional pruning methods for deep neural networks are not tailored to the unique characteristics of LDMs, such as the high computational …

abstract arxiv challenges computational consumption cs.ai cs.cv cs.lg devices diffusion diffusion models generative generative models however inference insights issue latent diffusion models memory memory consumption presenting pruning resources results speed type