一致性模型中的不一致性：更好的ODE求解并不意味着更好的样本

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples

November 13, 2024

作者: Noël Vouitsis, Rasa Hosseinzadeh, Brendan Leigh Ross, Valentin Villecroze, Satya Krishna Gorti, Jesse C. Cresswell, Gabriel Loaiza-Ganem

cs.AI

摘要

尽管扩散模型能够生成质量极高的样本，但由于其昂贵的迭代抽样过程，存在固有瓶颈。一致性模型（CMs）最近作为一种有前景的扩散模型蒸馏方法出现，通过在几次迭代中生成高保真度样本来降低抽样成本。一致性模型蒸馏旨在解决由现有扩散模型定义的概率流普通微分方程（ODE）。CMs并非直接经过训练以最小化针对ODE求解器的误差，而是采用更易于计算的客观函数。为了研究CMs如何有效解决概率流ODE以及任何引发的误差对生成样本质量的影响，我们引入了直接CMs，直接最小化这种误差。有趣的是，我们发现与CMs相比，直接CMs减少了ODE求解误差，但也导致生成样本质量显著下降，这引发了对CMs究竟为何起初表现良好的质疑。完整代码可在以下链接找到：https://github.com/layer6ai-labs/direct-cms。

English

Although diffusion models can generate remarkably high-quality samples, they are intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency models (CMs) have recently emerged as a promising diffusion model distillation method, reducing the cost of sampling by generating high-fidelity samples in just a few iterations. Consistency model distillation aims to solve the probability flow ordinary differential equation (ODE) defined by an existing diffusion model. CMs are not directly trained to minimize error against an ODE solver, rather they use a more computationally tractable objective. As a way to study how effectively CMs solve the probability flow ODE, and the effect that any induced error has on the quality of generated samples, we introduce Direct CMs, which directly minimize this error. Intriguingly, we find that Direct CMs reduce the ODE solving error compared to CMs but also result in significantly worse sample quality, calling into question why exactly CMs work well in the first place. Full code is available at: https://github.com/layer6ai-labs/direct-cms.