Effective Quantization for Diffusion Models on CPUs
This work addresses the computational resource challenge for diffusion models, enabling faster and more efficient image generation on CPUs, though it appears incremental as it builds on existing quantization techniques.
The paper tackles the challenge of quantizing diffusion models for efficient CPU inference by introducing a novel approach combining quantization-aware training and distillation, achieving maintained high image quality with demonstrated inference efficiency.
Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes. Quantization, a technique employed to compress deep learning models for enhanced efficiency, presents challenges when applied to diffusion models. These models are notably more sensitive to quantization compared to other model types, potentially resulting in a degradation of image quality. In this paper, we introduce a novel approach to quantize the diffusion models by leveraging both quantization-aware training and distillation. Our results show the quantized models can maintain the high image quality while demonstrating the inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.