---
license: cc-by-nc-nd-4.0
arxiv: 2311.11255
extra_gated_prompt: >-
  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.
extra_gated_fields:
  Full Name: text
  Gender: text
  Institution: text
  Group: text
  Contact Email: text
  Github: text
  Personal Homepage: text
  Use Case: text
  I agree to use this dataset for non-commercial use ONLY: checkbox
tags:
- music
---
# 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](https://github.com/crypto-code/MU-LLaMA) and [VideoMAE captioning](https://huggingface.co/Neleac/timesformer-gpt2-video-captioning) models.
This dataset is used to train the [M<sup>2</sup>UGen](https://github.com/crypto-code/M2UGen) model.

The [MUVideoInstructions.json](./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"
    }
  ]
}
```