利用扩散变换器内部动力学引导自身生成过程

摘要

扩散模型展现出强大的（条件）数据分布捕捉能力。然而，由于缺乏足够训练数据和低概率区域覆盖能力，模型在生成这些区域对应的高质量图像时会受到惩罚。为提升生成质量，分类器无引导（CFG）等策略可在采样阶段将样本导向高概率区域，但标准CFG常导致样本过度简化或失真。另一类通过劣化版本引导扩散模型的方法，则受限于精心设计的退化策略、额外训练和附加采样步骤。本文提出简单有效的内部引导（IG）策略，通过在训练阶段引入中间层辅助监督，并在采样阶段外推中间层与深层输出来获得生成结果。该策略在多种基线模型上显著提升了训练效率和生成质量：在ImageNet 256×256数据集上，SiT-XL/2+IG在80和800轮训练时分别达到FID=5.31和FID=1.75；更令人瞩目的是，LightningDiT-XL/1+IG实现FID=1.34，大幅领先现有方法。结合CFG后，LightningDiT-XL/1+IG更以1.19的FID刷新当前最优纪录。

English

The diffusion model presents a powerful ability to capture the entire (conditional) data distribution. However, due to the lack of sufficient training and data to learn to cover low-probability areas, the model will be penalized for failing to generate high-quality images corresponding to these areas. To achieve better generation quality, guidance strategies such as classifier free guidance (CFG) can guide the samples to the high-probability areas during the sampling stage. However, the standard CFG often leads to over-simplified or distorted samples. On the other hand, the alternative line of guiding diffusion model with its bad version is limited by carefully designed degradation strategies, extra training and additional sampling steps. In this paper, we proposed a simple yet effective strategy Internal Guidance (IG), which introduces an auxiliary supervision on the intermediate layer during training process and extrapolates the intermediate and deep layer's outputs to obtain generative results during sampling process. This simple strategy yields significant improvements in both training efficiency and generation quality on various baselines. On ImageNet 256x256, SiT-XL/2+IG achieves FID=5.31 and FID=1.75 at 80 and 800 epochs. More impressively, LightningDiT-XL/1+IG achieves FID=1.34 which achieves a large margin between all of these methods. Combined with CFG, LightningDiT-XL/1+IG achieves the current state-of-the-art FID of 1.19.

利用扩散变换器内部动力学引导自身生成过程

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

摘要

Support