Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

Understand

We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g.

• $1024 \times 1024$) directly in pixel-space.
• Building on the Transformer architecture, which is known to scale to billions of parameters, it bridges the gap between the efficiency of convolutional U-Nets and the scalability of Transformers.
• HDiT trains successfully without typical high-resolution training techniques such as multiscale architectures, latent autoencoders or self-conditioning.