JVID: Joint Video-Image Diffusion for Visual-Quality and Temporal-Consistency in Video Generation

TL;DR

JVID introduces a joint diffusion approach combining image and video models to generate high-quality, temporally consistent videos, significantly improving realism and coherence in video synthesis.

Contribution

The paper presents a novel joint diffusion framework that integrates image and video diffusion models for improved video quality and temporal consistency.

Findings

Enhanced video realism and coherence demonstrated.

Quantitative improvements over existing methods.

Qualitative analysis confirms better temporal stability.

Abstract

We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos. We achieve this by integrating two diffusion models: a Latent Image Diffusion Model (LIDM) trained on images and a Latent Video Diffusion Model (LVDM) trained on video data. Our method combines these models in the reverse diffusion process, where the LIDM enhances image quality and the LVDM ensures temporal consistency. This unique combination allows us to effectively handle the complex spatio-temporal dynamics in video generation. Our results demonstrate quantitative and qualitative improvements in producing realistic and coherent videos.