Diffusion models (DMs) excel in image generation, but suffer from slow inference and the training-inference discrepancies. Although gradient-based solvers like DPM-Solver accelerate the denoising inference, they lack theoretical foundations in information transmission efficiency. In this work, we introduce an information-theoretic perspective on the inference processes of DMs, revealing that successful denoising fundamentally reduces conditional entropy in reverse transitions. This principle leads to our key insights into the inference processes: (1) data prediction parameterization outperforms its noise counterpart, and (2) optimizing conditional variance offers a reference-free way to minimize both transition and reconstruction errors. Based on these insights, we propose an entropy-aware variance optimized method for the generative process of DMs, called EVODiff, which systematically reduces uncertainty by optimizing conditional entropy during denoising. Extensive experiments on DMs validate our insights and demonstrate that our method significantly and consistently outperforms state-of-the-art (SOTA) gradient-based solvers. For example, compared to the DPM-Solver++, EVODiff reduces the reconstruction error by up to 45.5\% (FID improves from 5.10 to 2.78) at 10 function evaluations (NFE) on CIFAR-10, cuts the NFE cost by 25\% (from 20 to 15 NFE) for high-quality samples on ImageNet-256, and improves text-to-image generation while reducing artifacts. Code is available at https://github.com/ShiguiLi/EVODiff.

翻译：扩散模型在图像生成方面表现出色，但其推理速度缓慢且存在训练-推理不一致的问题。尽管基于梯度的求解器（如DPM-Solver）加速了去噪推理过程，但它们在信息传输效率方面缺乏理论基础。本文从信息论视角审视扩散模型的推理过程，揭示了成功的去噪本质上是通过逆向转移降低条件熵。这一原理引出了我们对推理过程的关键洞见：（1）数据预测参数化方法优于噪声预测参数化方法；（2）优化条件方差提供了一种无需参考即可最小化转移误差与重建误差的途径。基于这些洞见，我们提出了一种用于扩散模型生成过程的熵感知方差优化方法——EVODiff，该方法通过在去噪过程中优化条件熵来系统性地降低不确定性。在扩散模型上的大量实验验证了我们的观点，并证明该方法显著且持续地优于当前最先进的基于梯度求解器。例如，在CIFAR-10数据集上，与DPM-Solver++相比，EVODiff在10次函数评估（NFE）时将重建误差降低达45.5%（FID从5.10提升至2.78）；在ImageNet-256数据集上，为获得高质量样本将NFE成本降低25%（从20次NFE降至15次NFE）；同时在提升文本到图像生成质量的同时减少了伪影。代码发布于https://github.com/ShiguiLi/EVODiff。