The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion

TL;DR

The paper introduces TPoS, a novel audio-reactive video generation model that leverages stable diffusion and audio embeddings to produce videos synchronized with audio input, advancing audio-to-video synthesis.

Contribution

The paper presents a new method combining stable diffusion with audio embeddings for audio-reactive video generation, addressing the gap in audio-to-video synthesis.

Findings

Effective audio-reactive video generation demonstrated

Outperforms current state-of-the-art techniques

Versatile across various tasks

Abstract

In recent years, video generation has become a prominent generative tool and has drawn significant attention. However, there is little consideration in audio-to-video generation, though audio contains unique qualities like temporal semantics and magnitude. Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude. To generate video frames, TPoS utilizes a latent stable diffusion model with textual semantic information, which is then guided by the sequential audio embedding from our pretrained Audio Encoder. As a result, this method produces audio reactive video contents. We demonstrate the effectiveness of TPoS across various tasks and compare its results with current state-of-the-art techniques in the field of audio-to-video generation. More examples are available at https://ku-vai.github.io/TPoS/