Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users. At the core of our innovations is a new conditional score function at the patch level, where the patch location in the original image is included as additional coordinate channels, while the patch size is randomized and diversified throughout training to encode the cross-region dependency at multiple scales. Sampling with our method is as easy as in the original diffusion model. Through Patch Diffusion, we could achieve $\mathbf{\ge 2\times}$ faster training, while maintaining comparable or better generation quality. Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e.g.$, as few as 5,000 images to train from scratch. We achieve state-of-the-art FID scores 1.77 on CelebA-64$\times$64 and 1.93 on AFHQv2-Wild-64$\times$64. We will share our code and pre-trained models soon.

提出了一种名为Patch Diffusion的通用Patch-wise训练框架，其核心创新是新的条件分数函数，它在原始图像的Patch级别包括Patch位置作为附加坐标通道，并且通过训练在多个尺度上对Patch大小进行随机和多样化，从而达到显著减少训练时间成本同时提高数据效率以帮助更广泛的用户学习扩散模型。

Patch Diffusion：扩散模型的更快、更省数据训练