无需训练，无问题：重新思考扩散模型的无分类器指导

摘要

无分类器引导（CFG）已成为提升条件扩散模型质量的标准方法。然而，使用CFG要么需要在主扩散模型旁训练一个无条件模型，要么通过定期插入空条件修改训练过程。目前CFG在无条件模型上的扩展也并不明确。本文重新审视CFG的核心原则，并引入一种新方法，独立条件引导（ICG），它提供了CFG的好处，而无需任何特殊的训练程序。我们的方法简化了条件扩散模型的训练过程，并且可以应用于任何预训练的条件模型推断过程中。此外，通过利用所有扩散网络中编码的时间步信息，我们提出了一种CFG的扩展，称为时间步引导（TSG），可应用于任何扩散模型，包括无条件模型。我们的引导技术易于实现，并且具有与CFG相同的采样成本。通过大量实验证明，ICG在各种条件扩散模型上与标准CFG的性能相匹敌。此外，我们展示了TSG如何提高生成质量，类似于CFG，而无需依赖任何条件信息。

English

Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.

无需训练，无问题：重新思考扩散模型的无分类器指导

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

摘要

Support