Diffusion models have achieved great success due to their remarkable
generation ability. However, their high computational overhead is still a
troublesome problem. Recent studies have leveraged post-training quantization
(PTQ) to compress diffusion models. However, most of them only focus on
unconditional models, leaving the quantization of widely used large pretrained
text-to-image models, e.g., Stable Diffusion, largely unexplored. In this
paper, we propose a novel post-training quantization method PCR (Progressive
Calibration and Relaxing) for text-to-image diffusion models, which consists of
a progressive calibration strategy that considers the accumulated quantization
error across timesteps, and an activation relaxing strategy that improves the
performance with negligible cost. Additionally, we demonstrate the previous
metrics for text-to-image diffusion model quantization are not accurate due to
the distribution gap. To tackle the problem, we propose a novel QDiffBench
benchmark, which utilizes data in the same domain for more accurate evaluation.
Besides, QDiffBench also considers the generalization performance of the
quantized model outside the calibration dataset. Extensive experiments on
Stable Diffusion and Stable Diffusion XL demonstrate the superiority of our
method and benchmark. Moreover, we are the first to achieve quantization for
Stable Diffusion XL while maintaining the performance.

我们提出了一种新的文本到图像扩散模型的后训练量化方法 PCR（渐进校准和放松），它包括了一种渐进校准策略，考虑了时间步长上的积累量化误差，以及一种激活放松策略，在性能提升方面几乎没有成本。另外，我们展示了文本到图像扩散模型量化的先前度量不准确的问题，并提出了一种新的 QDiffBench 基准，利用相同领域的数据进行更准确的评估。此外，QDiffBench 还考虑了量化模型在校准数据集之外的泛化性能。对 Stable Diffusion 和 Stable Diffusion XL 的广泛实验证明了我们的方法和基准的优越性。此外，我们是首次在保持性能的同时实现了 Stable Diffusion XL 的量化。