The recent wave of AI-generated content has witnessed the great development and success
of Text-to-Image (T2I) technologies. By contrast Text-to-Video (T2V) still falls short of …

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a
pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task …

Generating temporally coherent high fidelity video is an important milestone in generative
modeling research. We make progress towards this milestone by proposing a diffusion …

We introduce a novel generative model for video prediction based on latent flow matching,
an efficient alternative to diffusion-based models. In contrast to prior work, we keep the high …

We present an efficient text-to-video generation framework based on latent diffusion models,
termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with …

Abstract We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various
video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video …

Despite the remarkable progress in deep generative models, synthesizing high-resolution
and temporally coherent videos still remains a challenge due to their high-dimensionality …

We propose Latent-Shift--an efficient text-to-video generation method based on a pretrained
text-to-image generation model that consists of an autoencoder and a U-Net diffusion model …

In the deep learning era, long video generation of high-quality still remains challenging due
to the spatio-temporal complexity and continuity of videos. Existing prior works have …

In this paper we introduce Fairy a minimalist yet robust adaptation of image-editing diffusion
models enhancing them for video editing applications. Our approach centers on the concept …