Abstract Text-to-image (T2I) diffusion models notably the unCLIP models (eg DALL-E-2)
achieve state-of-the-art (SOTA) performance on various compositional T2I benchmarks at …

The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated
strong power of learning complex structures and meaningful semantics. However, relying …

Despite their ability to generate high-resolution and diverse images from text prompts text-to-
image diffusion models often suffer from slow iterative sampling processes. Model distillation …

Text-conditioned image generation models have recently shown immense qualitative
success using denoising diffusion processes. However, unlike discriminative vision-and …

Recent strides in the development of diffusion models exemplified by advancements such as
Stable Diffusion have underscored their remarkable prowess in generating visually …

Abstract Text-to-image (T2I) generative models have recently emerged as a powerful tool
enabling the creation of photo-realistic images and giving rise to a multitude of applications …

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have
shown promising performance in various computer vision tasks. However, these emerging …

Diffusion models (DMs) have become the new trend of generative models and have
demonstrated a powerful ability of conditional synthesis. Among those, text-to-image …

Despite the recent advances in personalized text-to-image (P-T2I) generative models,
subject-driven T2I remains challenging. The primary bottlenecks include 1) Intensive training …

This study explores the role of cross-attention during inference in text-conditional diffusion
models. We find that cross-attention outputs converge to a fixed point after few inference …