We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution. This model has the following advantages: 1) For sampling, it generates a fake image with only one step forward. 2) For training, it only needs 10 diffusion steps.3) Compared with consistency model, it is free of the ill-posed problem caused by consistency loss. On the popular CIFAR-10 dataset, our model outperforms Consistency Model and Denoising Score Matching, which demonstrates the potential of the framework. We further provide more examples on the MINIST and LSUN datasets. The code is available on GitHub.

翻译：我们提出了一种基于分数的新模型，该模型支持单步采样。此前，基于分数的模型因迭代采样而面临沉重的计算负担。为替代迭代过程，我们训练一个独立的生成器，利用从分数网络反向传播的梯度来压缩所有时间步。为了向生成器提供有意义的梯度，分数网络被训练为同时匹配真实数据分布并失配假数据分布。该模型具有以下优势：1）采样时，仅需单步前向传播即可生成假图像；2）训练时，仅需10个扩散步骤；3）与一致性模型相比，它避免了一致性损失带来的病态问题。在流行的CIFAR-10数据集上，我们的模型优于一致性模型和去噪分数匹配，展现了该框架的潜力。我们进一步在MNIST和LSUN数据集上提供了更多示例。代码已发布在GitHub上。