---
license: mit
model_type: diffusers
tags:
- music
- art
- text-to-audio
language:
- en
datasets:
- seungheondoh/LP-MusicCaps-MSD
- DynamicSuperb/MusicGenreClassification_FMA
- DynamicSuperb/MARBLEMusicTagging_MagnaTagATune
- agkphysics/AudioSet
pipeline_tag: text-to-audio
---

## Model Description

This model allows for easy setup and usage for generating music from text prompts.

## How to Use

refer to : https://github.com/ivcylc/qa-mdt 
with huggingface space