Abstract We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that
efficiently samples large-scale foundational image diffusion models in just 1–4 steps while …

Diffusion models currently dominate the field of data-driven image synthesis with their
unparalleled scaling to large datasets. In this paper we identify and rectify several causes for …

The primary axes of interest in image-generating diffusion models are image quality, the
amount of variation in the results, and how well the results align with a given condition, eg, a …

The diffusion model has long been plagued by scalability and quadratic complexity issues,
especially within transformer-based structures. In this study, we aim to leverage the long …

Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T)
research. However, current datasets lack descriptions with fine-grained detail that would …

Guidance is a crucial technique for extracting the best performance out of image-generating
diffusion models. Traditionally, a constant guidance weight has been applied throughout the …

We address the task of generating temporally consistent and physically plausible images of
actions and object state transformations. Given an input image and a text prompt describing …

Most of the existing diffusion models use Gaussian noise for training and sampling across all
time steps, which may not optimally account for the frequency contents reconstructed by the …

Rapid progress in text-to-image generative models coupled with their deployment for visual
content creation has magnified the importance of thoroughly evaluating their performance …

In response to everyday queries, humans explicitly signal uncertainty and offer alternative
answers when they are unsure. Machine learning models that output calibrated prediction …