Modern diffusion models, particularly those utilizing a Transformer-based UNet for
denoising, rely heavily on self-attention operations to manage complex spatial relationships …

The potential for higher-resolution image generation using pretrained diffusion models is
immense, yet these models often struggle with issues of object repetition and structural …

Large-scale generative models, such as text-to-image diffusion models, have garnered
widespread attention across diverse domains due to their creative and high-fidelity image …

We present the Generalized Spatial Propagation Network (GSPN), a new attention
mechanism optimized for vision tasks that inherently captures 2D spatial structures. Existing …

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited
resolutions due to the lack of high-resolution data and constrained computation resources …

Diffusion models are proficient at generating high-quality images. They are however
effective only when operating at the resolution used during training. Inference at a scaled …

Diffusion models suffer severe object repetition and local distortion when the inference
resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate …