Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation

TL;DR

Art2Mus introduces a novel AI model that generates music from digitized artworks or text, extending cross-modal creativity beyond simple images and enabling new multimedia artistic applications.

Contribution

It extends the AudioLDM 2 architecture to create a model capable of generating music from complex digitized artworks, using curated datasets from ImageBind.

Findings

Successfully generates music aligned with input artworks

Demonstrates potential for multimedia art and interactive installations

Shows promising results in cross-modal creative applications

Abstract

Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$, a novel model designed to create music from digitized artworks or text inputs. $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ extends the AudioLDM~2 architecture, a text-to-audio model, and employs our newly curated datasets, created via ImageBind, which pair digitized artworks with music. Experimental results demonstrate that $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ can generate music that resonates with the input stimuli. These findings suggest promising applications in multimedia art, interactive installations, and AI-driven creative tools.