We propose 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.
![](https://github.com/amaai-lab.png)
amaai-lab
/
video2music
Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model