You need to agree to share your contact information to access this dataset

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Please fill in the following fields, the full name/institution/group/contact email/use case are MUST fields, and gender/github/personal homepage are OPTIONAL fields (You can simply use a '-' symbol to fill in these optional fields). An application form without required information will be declined.

MUVideo Dataset

This is the MUVideo dataset used to facilitate image to music generation, consisting of 13,203 music files with a total playtime of 36.72 hours generated using the MU-LLaMA and VideoMAE captioning models. This dataset is used to train the M²UGen model.

The MUVideoInstructions.json file contains a list with each of the element having the following format:

{
  "input_file": "1OhKgYcAujk.mp4",
  "output_file": "1OhKgYcAujk.mp3",
  "conversation": [
    {
      "from": "human",
      "value": "Generate a music for the video that is upbeat and energetic to match the guitar playing in the living room.",
      "input_modality": "video",
      "caption": "A man is playing a song on a guitar while sitting in a living room with a couch."
    },
    {
      "from": "gpt",
      "value": "Here is a music that is a solo upright bass playing a blues melody.",
      "caption": "The music is a solo upright bass playing a blues melody.",
      "output_modality": "audio"
    }
  ]
}

Datasets:

M2UGen
/

MUVideo

You need to agree to share your contact information to access this dataset

MUVideo Dataset

Models trained or fine-tuned on M2UGen/MUVideo

M2UGen/M2UGen-MusicGen-medium