RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance

TL;DR

This paper introduces RISSOLE, a parameter-efficient diffusion model that uses block-wise generation and retrieval-guidance to produce coherent images with fewer parameters, suitable for resource-limited devices.

Contribution

The paper proposes a retrieval-augmented block-wise diffusion approach that ensures coherence across image blocks, enabling compact yet high-quality image generation.

Findings

Achieves high-quality image generation with fewer parameters.

Ensures coherence across blocks through retrieval-guided conditioning.

Demonstrates effectiveness on latent diffusion models.

Abstract

Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices. Block-wise generation can be a promising alternative for designing compact-sized (parameter-efficient) deep generative models since the model can generate one block at a time instead of generating the whole image at once. However, block-wise generation is also considerably challenging because ensuring coherence across generated blocks can be non-trivial. To this end, we design a retrieval-augmented generation (RAG) approach and leverage the corresponding blocks of the images retrieved by the RAG module to condition the training and generation stages of a block-wise denoising diffusion model. Our conditioning schemes ensure coherence across the different blocks during training and, consequently, during generation. While we showcase our approach using the latent diffusion model (LDM) as the base model, it can be used with other variants of denoising diffusion models. We validate the solution of the coherence problem through the proposed approach by reporting substantive experiments to demonstrate our approach's effectiveness in compact model size and excellent generation quality.