TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models

arXiv:2404.09532v1 Announce Type: cross
Abstract: Diffusion models have emerged as preeminent contenders in the realm of generative models. Distinguished by their distinctive sequential generative processes, characterized by hundreds or even thousands of timesteps, diffusion models progressively reconstruct images from pure Gaussian noise, with each timestep necessitating full inference of the entire model. However, the substantial computational demands inherent to these models present challenges for deployment, quantization is thus widely used to lower the bit-width for reducing the storage and computing …

abstract arxiv cs.cv cs.lg diffusion diffusion models generative generative models images inference noise precision processes quantization realm type