用调制量化加速扩散模型，3比特压缩仍保生成质量
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
- 通过调制量化与误差补偿实现高效采样
- 在CIFAR-10和LSUN上实现8位到3位量化无性能损失
- 通用框架适配各类扩散模型，适合部署优化场景
扩散模型虽强大，但迭代采样计算开销大。本文深入研究现有加速技术（缓存与量化），揭示其在计算误差与生成质量上的局限。为此提出模制扩散（MoDiff）——一种基于调制量化与误差补偿的新型原则性框架，兼具已有方法优势并可通用加速所有扩散模型。理论分析支持其有效性。大量实验表明，在CIFAR-10和LSUN数据集上，后训练量化中激活值可从8位降至3位，且不降低生成性能。代码已开源：https://github.com/WeizhiGao/MoDiff。
原文摘要 · Abstract (English)
Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration techniques for diffusion models, including caching and quantization, revealing their limitations in computation error and generation quality. To break these limits, this work introduces Modulated Diffusion (MoDiff), an innovative, rigorous, and principled framework that accelerates generative modeling through modulated quantization and error compensation. MoDiff not only inherents the advantages of existing caching and quantization methods but also serves as a general framework to accelerate all diffusion models. The advantages of MoDiff are supported by solid theoretical insight and analysis. In addition, extensive experiments on CIFAR-10 and LSUN demonstrate that MoDiff significant reduces activation quantization from 8 bits to 3 bits without performance degradation in post-training quantization (PTQ). Our code implementation is available at https://github.com/WeizhiGao/MoDiff.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。