Diffusion models excel in high-quality generation but suffer from slow inference due to
iterative sampling. While recent methods have successfully transformed diffusion models …

Recent years have seen an explosion of work and interest in text‐to‐3D shape generation.
Much of the progress is driven by advances in 3D representations, large‐scale pretraining …

Diffusion models are trained by learning a sequence of models that reverse each step of
noise corruption. Typically, the model parameters are fully shared across multiple timesteps …

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation
poses a significant hurdle for its practical application. To tackle this challenge, recent …

The evolution of 3D generative modeling has been notably propelled by the adoption of 2D
diffusion models. Despite this progress, the cumbersome optimization process per se …

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 …

The high computational cost and slow inference time are major obstacles to deploying the
video diffusion model (VDM) in practical applications. To overcome this, we introduce a new …

Text-to-video generation enhances content creation but is highly computationally intensive:
The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number …

Conditional image synthesis based on user-specified requirements is a key component in
creating complex visual content. In recent years, diffusion-based generative modeling has …

Recent advancements in text-to-image diffusion models have enabled the personalization of
these models to generate custom images from textual prompts. This paper presents an …