Diffusion models have been proven highly effective at generating high-quality images.
However, as these models grow larger, they require significantly more memory and suffer …

We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free
approach for DiT-based video generation. Our method is founded on the observation that …

Diffusion Transformers have emerged as the preeminent models for a wide array of
generative tasks, demonstrating superior performance and efficacy across various …

Diffusion transformers have shown significant effectiveness in both image and video
synthesis at the expense of huge computation costs. To address this problem, feature …

The increased model capacity of Diffusion Transformers (DiTs) and the demand for
generating higher resolutions of images and videos have led to a significant rise in inference …

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation
quality but suffer from high latency and memory inefficiency, making them difficult to deploy …

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-
image synthesis; however, their iterative denoising process demands substantial …

Diffusion models have achieved impressive advancements in various vision tasks. However,
these gains often rely on increasing model size, which escalates computational complexity …

As a fundamental backbone for video generation, diffusion models are challenged by low
inference speed due to the sequential nature of denoising. Previous methods speed up the …

Diffusion models are pivotal for generating high-quality images and videos. Inspired by the
success of OpenAI's Sora, the backbone of diffusion models is evolving from U-Net to …