再进一步：一个用于修正扩散调度缺陷并增强低频控制的多功能即插即用模块
One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls
AI总结：
本文提出One More Step (OMS)模块，通过集成紧凑网络并在推理时增加一步，无需修改预训练模型即可修正扩散调度缺陷，提升图像保真度并协调训练与推理的不一致性。
摘要：
众所周知，许多开源的基础扩散模型在生成大幅偏离平均亮度的图像时存在困难，尽管此类图像在训练数据中存在。这是由于一种不一致性：推理期间去噪从纯高斯噪声开始，但由于主流公式中数值调节的困难，训练噪声调度在最终时间步分布中仍保留残差数据，导致推理期间出现意外偏差。为缓解此问题，某些ε-预测模型与临时偏移噪声方法相结合。同时，一些当代模型采用零终端信噪比（SNR）噪声调度和v-预测，这需要对预训练模型进行重大修改。然而，此类修改可能破坏大量基于这些预训练模型的社区驱动应用。鉴于此，我们的研究重新审视了根本原因，并提出了一种创新且原则性的补救措施，称为One More Step (OMS)。通过集成一个紧凑网络并在推理期间引入一个额外简单有效的步骤，OMS在保留原始模型参数的同时提升了图像保真度，并协调了训练与推理之间的二分性。一旦训练完成，具有相同潜在域的各种预训练扩散模型可以共享同一个OMS模块。
英文摘要：
It is well known that many open-released foundational diffusion models have difficulty in generating images that substantially depart from average brightness, despite such images being present in the training data. This is due to an inconsistency: while denoising starts from pure Gaussian noise during inference, the training noise schedule retains residual data even in the final timestep distribution, due to difficulties in numerical conditioning in mainstream formulation, leading to unintended bias during inference. To mitigate this issue, certain $ε$-prediction models are combined with an ad-hoc offset-noise methodology. In parallel, some contemporary models have adopted zero-terminal SNR noise schedules together with $\mathbf{v}$-prediction, which necessitate major alterations to pre-trained models. However, such changes risk destabilizing a large multitude of community-driven applications anchored on these pre-trained models. In light of this, our investigation revisits the fundamental causes, leading to our proposal of an innovative and principled remedy, called One More Step (OMS). By integrating a compact network and incorporating an additional simple yet effective step during inference, OMS elevates image fidelity and harmonizes the dichotomy between training and inference, while preserving original model parameters. Once trained, various pre-trained diffusion models with the same latent domain can share the same OMS module.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
