We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generative trajectories for $N$ dimensional data by embedding paths in $N{+}D$ dimensional space while still controlling the progression with a simple scalar norm of the $D$ additional variables. The new models reduce to PFGM when $D{=}1$ and to diffusion models when $D{\to}\infty$. The flexibility of choosing $D$ allows us to trade off robustness against rigidity as increasing $D$ results in more concentrated coupling between the data and the additional variable norms. We dispense with the biased large batch field targets used in PFGM and instead provide an unbiased perturbation-based objective similar to diffusion models. To explore different choices of $D$, we provide a direct alignment method for transferring well-tuned hyperparameters from diffusion models ($D{\to} \infty$) to any finite $D$ values. Our experiments show that models with finite $D$ can be superior to previous state-of-the-art diffusion models on CIFAR-10/FFHQ $64{\times}64$ datasets, with FID scores of $1.91/2.43$ when $D{=}2048/128$. In class-conditional setting, $D{=}2048$ yields current state-of-the-art FID of $1.74$ on CIFAR-10. In addition, we demonstrate that models with smaller $D$ exhibit improved robustness against modeling errors. Code is available at https://github.com/Newbeeer/pfgmpp
翻译:我们引入了一套新的物理学启发型基因模型,称为PFGGG++,它统一了扩散模型和Poisson 流动模型(PFGM),这些模型通过将路径嵌入$N ⁇ D$的天体空间,同时仍然用一个简单的卡路里标准来控制增产过程,同时以美元的额外变量的简单卡路里标准来控制增产过程。新模型在$D1美元时会降低到PFGM,当美元美元为128美元时会降低到PFGM。选择美元的灵活性使得我们能够用强力来抵消硬性(美元)增加的数据和Poisson 流动模型(PFGM)。这些模型通过在数据和其他变量规范之间更加集中的混合,实现了美元更集中的元数据。我们通过在PFFGMGM中使用的偏差大批野外目标,而不是提供类似于扩散模型的无偏颇的围足目标。为了探索不同的选择,我们提供了一种直接的校准方法,将经过良好调整的超标从扩散模型(D美元)20美元(美元)的美元为美元)的美元(美元)的美元(美元)和每平流化模型展示的美元)的美元(美元)的美元(美元)的美元)和每平价的美元(美元)的美元(美元)的美元)的美元)的美元(美元)的美元)的美元(美元)的美元),在任何固定值值值。我们的美元(美元)的美元(美元)的模型上展示。我们的基化模型上,在我們FRFFIRFRFRFRFDFRFDFDFDRFDRFD)的模型上展示。