GitHub radar
[PRESS RELEASE] YuE2 music generator in ComfyUI!
Comfy-Org turned the m-a-p YuE2-3B music generation model into a native ComfyUI node! Just give it a mood/genre, and you’ll receive a song!
Comfy-Org has launched the ComfyUI Node of the m-a-p YuE2-3B Music Generation Model. The YuE2 Music Generation Model accepts a textual description about the desired mood and genre of the music and generates music, such as melodies, drum beats, instrument sounds, etc. The model consists of SheetSage2 Audio Encoder and the main model. Simply copy these files to your ComfyUI checkpoints folder and audio_encoders folder to get started! This model is available under a cc-by-nc-4.0 license, which means you can’t use this model commercially. People in the community are using this model to create Ambient, Lo-Fi, and Pop music. Since this is a 3B model, the audio quality is decent for creating content but not good enough for professional music production.
Why a vibe-coder should care
With this model, you can now use one platform (such as ComfyUI) to generate images, videos, and music! Perfect for content creators who want to create videos with background music for reels and short videos. No need for a Suno account or any subscription fees! No API Keys Required!
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Set up the YuE2 music generation model for ComfyUI from Comfy-Org: https://huggingface.co/Comfy-Org/YuE2 — download both files, place them in the right folders, and show me how to open an example workflow and generate my first track.
A regular laptop with 16 GB of RAM — the bf16 model takes about 6 GB.
Open on Hugging Face▌ More finds