We introduce the Pyramid Diffusion Model (PDM), a novel architecture designed
for ultra-high-resolution image synthesis. PDM utilizes a pyramid latent
representation, providing a broader design space that enables more flexible,
structured, and efficient perceptual compression which enable AutoEncoder and
Network of Diffusion to equip branches and deeper layers. To enhance PDM's
capabilities for generative tasks, we propose the integration of
Spatial-Channel Attention and Res-Skip Connection, along with the utilization
of Spectral Norm and Decreasing Dropout Strategy for the Diffusion Network and
AutoEncoder. In summary, PDM achieves the synthesis of images with a 2K
resolution for the first time, demonstrated on two new datasets comprising
images of sizes 2048x2048 pixels and 2048x1024 pixels respectively. We believe
that this work offers an alternative approach to designing scalable image
generative models, while also providing incremental reinforcement for existing
frameworks.

Pyramid Diffusion Model (PDM) 通过金字塔潜在表示提供了更广泛的设计空间，以实现超高分辨率图像合成，结合空间通道注意力和 Res-Skip 连接，以及谱范数和递减的 Dropout 策略，使得 PDM 在生成任务方面具有更强的能力，首次成功合成了 2K 分辨率的图像。