AtomoVideo: High Fidelity Image-to-Video Generation

TL;DR

AtomoVideo is a high fidelity image-to-video generation framework that leverages multi-granularity image injection to produce videos with greater motion, temporal consistency, and stability, while being adaptable to long sequences and personalized models.

Contribution

The paper introduces a novel high fidelity image-to-video generation framework, AtomoVideo, with multi-granularity image injection and adaptable architecture for long sequences and personalization.

Findings

Achieves higher fidelity in generated videos compared to existing methods.

Maintains superior temporal consistency and stability in video outputs.

Enables long sequence prediction through iterative generation.

Abstract

Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques. In this work, we propose a high fidelity framework for image-to-video generation, named AtomoVideo. Based on multi-granularity image injection, we achieve higher fidelity of the generated video to the given image. In addition, thanks to high quality datasets and training strategies, we achieve greater motion intensity while maintaining superior temporal consistency and stability. Our architecture extends flexibly to the video frame prediction task, enabling long sequence prediction through iterative generation. Furthermore, due to the design of adapter training, our approach can be well combined with existing personalized models and controllable modules. By quantitatively and qualitatively evaluation, AtomoVideo achieves superior results compared to popular methods, more examples can be found on our project website: https://atomo-video.github.io/.