YuE2-3B Music Generator by x1205x62108

YuE2-3B Music Generator by x1205x62108

Generates songs and covers from a style prompt and lyrics with the YuE2-3B model, in the browser on Hugging Face or from a local copy. For musicians and creators who want quick song drafts.

Made by x1205x62108 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space generates songs and covers from a style prompt and lyrics. It is a Gradio app built around the YuE2-3B music model and runs on ZeroGPU hardware at Hugging Face. It also names helper models for audio decoding, sheet music analysis, text and speech recognition.

Who it suits: Musicians, hobbyists and content creators who want a quick song draft from words and a style description, without a studio setup.

Industry | Who uses it | How they use it | Example
Music | Songwriters | Hear a draft of lyrics set to music | Paste lyrics and describe a style
Content creation | Video creators | Make a custom track for a project | Ask for a mood and a genre
Hobby projects | Hobbyists | Try AI song and cover generation | Run the Space with a short lyric

People who need a finished, mastered release can skip it, and so can anyone who needs a license that allows commercial use.

Where to use it:

• A browser: the Space runs on Hugging Face with nothing to install
• Windows, macOS or Linux: run a copy of the Space with Python 3.10.13

Use case | Who | What they get back
Song from lyrics | Songwriters | A generated song in the style you describe
Cover | Hobbyists | A generated cover version
Background track | Video creators | A custom piece of music for a project

How to set it up:

• Python 3.10.13 with pip on Windows, macOS or Linux
• The Python packages listed in requirements.txt
• Nothing at all if you only use the Space in a browser

1. Install the Hugging Face hub package.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio 5.49.1 and the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download x1205x62108/yue2-3b --repo-type space --local-dir yue2-3b
cd yue2-3b
pip install gradio==5.49.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space page in a browser, or start your own copy with the command below. On the Gradio page you give a style prompt and lyrics, and the app generates a song or a cover.

python app.py

Example: You write a short set of lyrics and describe the style you want. The app generates a song from them, and you can listen to it in the browser.

For newcomers and experts: If you are new, open the Space and start with a few lines of lyrics and a short style description. Generation can take a while because the model is large.

For experts, the Space names m-a-p/YuE2-3B and m-a-p/YuE2-Vae for the music model and its decoder, m-a-p/SheetSage2, Qwen/Qwen3-4B and Qwen/Qwen3-ASR-1.7B. The repository holds app.py and two requirements files, with Python 3.10.13 pinned.

You write a style prompt and lyrics
The app passes them to YuE2-3B
The model generates the audio
You listen in the browser

Good to know:

• License: cc-by-nc-4
• Cost to run: none named
• Data it reaches: the prompts and lyrics you type, and the models it names
• Not for: none stated in the README

On Hugging Face, 13 November 2026

• Likes: 3
• Built with: gradio
• License: cc-by-nc-4.0

Links

• Space: https://huggingface.co/spaces/x1205x62108/yue2-3b
• Files: https://huggingface.co/spaces/x1205x62108/yue2-3b/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.