Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model

We are happy to announce Video2Music, a novel AI-powered multimodal music generation framework called Video2Music. This framework uniquely uses video features as conditioning input to generate matching music using a Transformer architecture. By employing cutting-edge technology, our system aims to provide video creators with a seamless and efficient solution for generating tailor-made background music.

Live demo on Replicate.
View on github.

Kang, J., Poria, S. & Herremans, D. (2023). Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model. arXiv preprint arXiv:2311.00968.

Numerous studies in the field of music generation have demonstrated impressive performance, yet virtually no models are able to directly generate music to match accompanying videos. In this work, we develop a generative music AI framework, Video2Music, that can match a provided video. We first curated a unique collection of music videos. Then, we analysed the music videos to obtain semantic, scene offset, motion, and emotion features. These distinct features are then employed as guiding input to our music generation model. We transcribe the audio files into MIDI and chords, and extract features such as note density and loudness. This results in a rich multimodal dataset, called MuVi-Sync, on which we train a novel Affective Multimodal Transformer (AMT) model to generate music given a video. This model includes a novel mechanism to enforce affective similarity between video and music. Finally, post-processing is performed based on a biGRU-based regression model to estimate note density and loudness based on the video features. This ensures a dynamic rendering of the generated chords with varying rhythm and volume. In a thorough experiment, we show that our proposed framework can generate music that matches the video content in terms of emotion. The musical quality, along with the quality of music-video matching is confirmed in a user study. The proposed AMT model, along with the new MuVi-Sync dataset, presents a promising step for the new task of music generation for videos.

Read paper - Listen to demo