Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Deep generative models have unlocked another profound realm of human creativity. By
capturing and generalizing patterns within data, we have entered the epoch of all …

This paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions
relevant to a set of multi-modal data in one model. Our key insight is–learning diffusion …

Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based
on a convolutional neural network (CNN) remains dominant in diffusion models. We design …

A class of generative models that unifies flow-based and diffusion-based methods is
introduced. These models extend the framework proposed in Albergo & Vanden-Eijnden …

A generative model based on a continuous-time normalizing flow between any pair of base
and target probability densities is proposed. The velocity field of this flow is inferred from the …

Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity
image generation while suffering from inefficient sampling. Recent works accelerate the …

Priors are essential for reconstructing images from noisy and/or incomplete measurements.
The choice of the prior determines both the quality and uncertainty of recovered images. We …

Guided sampling is a vital approach for applying diffusion models in real-world tasks that
embeds human-defined guidance during the sampling procedure. This paper considers a …

Consistency Models (CM)(Song et al., 2023) accelerate score-based diffusion model
sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To …