扩散模型推理慢是落地痛点，Dual-Rate Diffusion 用轻量网络复用特征，做图像生成的团队可以直接拿来加速现有模型，效果不打折。
Dual-Rate Diffusion 提出了一种新的扩散模型加速方法，通过交错执行一个稀疏更新的重上下文编码器和一个轻量去噪模型来降低推理成本。重编码器每几步提取一次高维特征，轻量模型则在每一步复用这些特征进行高效去噪。在 ImageNet 基准上，该方法在保持生成质量的同时将计算成本降低 2-4 倍。此外，该方法与蒸馏技术（如 Moment Matching Distillation）兼容，可进一步加速少步生成。
Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diffusion, a method to accelerate sampling by interleaving the execution of a heavy high-capacity context encoder and a light efficient denoising model. The context encoder is evaluated sparsely to extract high-dimensional features, which are effectively reused by the light denoising model at every step to refine the sample efficiently. This approach significantly accelerates inference without compromising sample quality. On ImageNet benchmarks, Dual-Rate Diffusion matches the performance of standard baselines while reducing computational cost by a factor of $2$-$4$. Furthermore, we demonstrate that our method is compatible with distillation techniques, such as Moment Matching Distillation, enabling further efficiency gains in few-step generation.