Abstract
One-Step Diffusion Models have demonstrated promising capability and fast inference in video super-resolution (VSR) for real-world. Nevertheless, the substantial model size and high computational cost of Diffusion Transformers (DiTs) limit downstream applications. While low-bit quantization is a common approach for model compression, the effectiveness of quantized models is challenged by the high dynamic range of input latent and diverse layer behaviors. To deal with these challenges, we introduce LSGQuant, a layer-sensitivity guided quantizing approach for one-step diffusion-based real-world VSR. Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations. Furthermore, we estimate layer sensitivity and implement a Variance-Oriented Layer Training Strategy (VOLTS) by analyzing layer-wise statistics in calibration. We also introduce Quantization-Aware Optimization (QAO) to jointly refine the quantized branch and a retained high-precision branch. Extensive experiments demonstrate that our method has nearly performance to origin model with full-precision and significantly exceeds existing quantization techniques. Code is available at: this https URL.
Abstract (translated)
一阶段扩散模型（One-Step Diffusion Models）在现实世界中的视频超分辨率（VSR）任务中展示了令人鼓舞的能力和快速的推理性能。然而，扩散变换器（DiTs）巨大的模型尺寸以及高昂的计算成本限制了其下游应用的发展。虽然低比特量化是常用的模型压缩方法，但输入潜变量的高动态范围及不同层的行为多样性对量化的有效性构成了挑战。 为应对这些挑战，我们提出了LSGQuant，这是一种基于层敏感度引导的一阶段扩散视频超分辨率（VSR）量化方法。我们的方法采用了动态范围自适应量化器（DRAQ），以适配视频令牌激活，并通过校准中的逐层统计分析来估计层的敏感性并实施基于方差导向的层训练策略（VOLTS）。此外，我们还引入了量化的感知优化（QAO）技术，用于同时精炼量化的分支和保留的高精度分支。 广泛的实验表明，我们的方法几乎能够达到原始全精度模型的表现水平，并且在现有量化技术的基础上有了显著提升。代码可在以下网址获得：this https URL.
URL
https://arxiv.org/abs/2602.03182
