ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Text-to-Image (T2I) models have made significant advancements in recent years, but they
still struggle to accurately capture intricate details specified in complex compositional …
still struggle to accurately capture intricate details specified in complex compositional …
VideoPhy: Evaluating Physical Commonsense for Video Generation
Recent advances in internet-scale video data pretraining have led to the development of text-
to-video generative models that can create high-quality videos across a broad range of …
to-video generative models that can create high-quality videos across a broad range of …
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
Recent advancements in text-to-image (T2I) models have greatly benefited from large-scale
datasets, but they also pose significant risks due to the potential generation of unsafe …
datasets, but they also pose significant risks due to the potential generation of unsafe …
Aligning Diffusion Models with Noise-Conditioned Perception
A Gambashidze, A Kulikov, Y Sosnin… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advancements in human preference optimization, initially developed for Language
Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt …
Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt …