Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models

TL;DR

This paper introduces a floating-point quantization approach for diffusion models that enhances image quality and reduces degradation compared to traditional integer quantization, especially at low bitwidths.

Contribution

It proposes a novel floating-point quantization method tailored for diffusion models, demonstrating superior image quality over integer quantization at similar bitwidths.

Findings

Floating-point quantization yields higher-quality images than integer methods.

8-bit floating-point quantization maintains near full-precision quality.

Minimal degradation observed with 4-bit weights and 8-bit activations.

Abstract

Diffusion models are emerging models that generate images by iteratively denoising random Gaussian noise using deep neural networks. These models typically exhibit high computational and memory demands, necessitating effective post-training quantization for high-performance inference. Recent works propose low-bitwidth (e.g., 8-bit or 4-bit) quantization for diffusion models, however 4-bit integer quantization typically results in low-quality images. We observe that on several widely used hardware platforms, there is little or no difference in compute capability between floating-point and integer arithmetic operations of the same bitwidth (e.g., 8-bit or 4-bit). Therefore, we propose an effective floating-point quantization method for diffusion models that provides better image quality compared to integer quantization methods. We employ a floating-point quantization method that was effective for other processing tasks, specifically computer vision and natural language tasks, and tailor it for diffusion models by integrating weight rounding learning during the mapping of the full-precision values to the quantized values in the quantization process. We comprehensively study integer and floating-point quantization methods in state-of-the-art diffusion models. Our floating-point quantization method not only generates higher-quality images than that of integer quantization methods, but also shows no noticeable degradation compared to full-precision models (32-bit floating-point), when both weights and activations are quantized to 8-bit floating-point values, while has minimal degradation with 4-bit weights and 8-bit activations.