YuE2-3B Music Generator

YuE2-3B Music Generator

Makes songs and covers from a style prompt and lyrics, using the YuE2-3B model in a browser page. It suits musicians and hobbyists who want to try AI song generation.

Made by mrfakename 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 page around the YuE2-3B model and runs on zero-a10g hardware at Hugging Face. The page names several other models it works with, including YuE2-Vae, SheetSage2, Qwen3-4B and Qwen3-ASR-1.7B.

Who it suits: It suits people who want to hear what an AI song model produces from their own lyrics, and developers who want a small example of a music model in a Gradio app.

Industry | Who uses it | How they use it | Example
Music | Songwriters and hobbyists | Turn written lyrics into a sung draft | Paste lyrics, describe the style and listen to the result
Content creation | Video and podcast makers | Make a short song for a project | Describe a mood and ask for a song to fit it
AI development | Developers | Study a Gradio app built around a music model | Read app.py and the requirements files

You can skip it if you need a studio-quality master or detailed control over every part of the song.

Where to use it: You can use it in these places:

• A browser: open the Space's page on Hugging Face and nothing needs installing.
• Windows, macOS or Linux: run your own copy with Python 3.10.13.

Use case | Who | What they get back
Song from lyrics | Songwriters | A generated song that follows your style prompt and lyrics
Covers | Hobbyists | A generated cover version

How to set it up: You need these first for a local copy:

• Python 3.10.13 and pip
• A machine able to run the models the Space names

The online page needs none of this. For your own copy, follow the steps below. The repository also has a pre-requirements.txt file.

1. Install the Hugging Face tools.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio at the version the Space uses, then the other packages.
5. Start the app.

pip install -U huggingface_hub
hf download mrfakename/yue2-3b --repo-type space --local-dir yue2-3b
cd yue2-3b
pip install gradio==6.17.3
pip install -r requirements.txt
python app.py

How to use it: Open the Space in a browser, or start your own copy with the command below. Then write a style prompt and your lyrics, and run the generator.

python app.py

Tool | What it does
python app.py | Starts the Gradio app on your own computer
hf download | Copies the Space's files to a local folder

Example: You write a style prompt describing the sound you want, paste in your lyrics and run the generator. The Space returns a song that follows that style and sings your lyrics.

For newcomers and experts: If you are new to this, start with a short style prompt and a few lines of lyrics. Listen to the result, then change the style words and try again.

If you know the field, the Space names five models: YuE2-3B, YuE2-Vae, SheetSage2, Qwen3-4B and Qwen3-ASR-1.7B. The source gives no more detail on how they fit together, so read app.py for the exact pipeline.

You write a style prompt
You add your lyrics
The Space runs its models on a GPU
You get a song or cover

Good to know: The source describes the Space in a single line, so most of what is here comes from Hugging Face's own record and the repository files.

• License: cc-by-nc-4
• Cost to run: none named
• Data it reaches: the lyrics and prompts you enter, and model files downloaded from Hugging Face

On Hugging Face, 13 November 2026

• Likes: 235
• Built with: gradio
• License: cc-by-nc-4.0

Links

• Space: https://huggingface.co/spaces/mrfakename/yue2-3b
• Files: https://huggingface.co/spaces/mrfakename/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.