This is the official repository for the paper "MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models".
If there is any problem related to the code running, please open an issue and I will help you as mush as I can.
https://bit.ly/musicmagus-demo
# clone project
git clone https://github.com/ldzhangyx/MusicMagus/
cd MusicMagus
# [OPTIONAL] create conda environment
conda create -n myenv python=3.11.7
conda activate myenv
# install pytorch according to instructions
# https://pytorch.org/get-started/
# install requirements
pip install -r requirements.txt
# clone project
git clone https://github.com/ldzhangyx/MusicMagus/
cd MusicMagus
# create conda environment and install dependencies
conda env create -f environment.yaml -n myenv
# activate conda environment
conda activate myenv
-
Set the
openai.key
value inaudioldm2/embedding_calculator.py
. -
Directly run
inference.ipynb
.
@misc{zhang2024musicmagus,
title={MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models},
author={Yixiao Zhang and Yukara Ikemiya and Gus Xia and Naoki Murata and Marco A. MartÃnez-RamÃrez and Wei-Hsiang Liao and Yuki Mitsufuji and Simon Dixon},
year={2024},
eprint={2402.06178},
archivePrefix={arXiv},
primaryClass={cs.SD}
}