Home Creators Posts Import Register Favorites Logout

Downloads

Content

Video : https://youtu.be/kzTo8pLUKJY

Video For Chinese : https://www.bilibili.com/video/BV1W8eL6qEgC/

Hey everyone. New video is up, and this one is about Yue 2, an open-source music generation model that just beat Suno on benchmarks.

Video : https://youtu.be/kzTo8pLUKJY

You give it a style prompt and lyrics, and it generates a full song with vocals and accompaniment. 48kHz stereo, English, Mandarin, Japanese, Korean. A 3.6-minute song takes about 71 seconds on an RTX 4090.

The interesting part: Yue 2 writes an ABC music notation score before it generates the audio. That means you can edit the chords, change the melody, and regenerate from your edits. Suno and Udio do not give you that. It is like having a sheet of music you can tweak before the performance.

I tested it in ComfyUI with the workflow from the video. The GGUF quantized version runs on 8 to 9 GB VRAM, so even a 4070 or 3080 can get in on this. Supporters, the full run guide is in the supporter post.

Links in the description. Model is on Hugging Face, ComfyUI version included.

— Benji

Resources:

- Yue 2 Model: https://huggingface.co/m-a-p/YuE2-3B

- ComfyUI Pack: https://huggingface.co/Comfy-Org/YuE2

- GGUF (low VRAM): https://huggingface.co/audio-cpp/Yue2-3B-GGUF

- Demo Page: https://map-yue2.github.io/

- GitHub: https://github.com/multimodal-art-projection/YuE

- Paper: https://arxiv.org/abs/2503.08638

Files

YuE2 Generate Full Songs In ComfyUI Locally - Open Source Suno Alternative

YuE2 is an open-source music generation AI that beats Suno v5 and v6 on benchmarks, with editable scores, cover mode, and full song output. Runs locally on a 24GB GPU or 8-9GB with GGUF quantization. This video covers the Yue2-3B music generation model, what makes it different from Suno and Udio, and how to use it through ComfyUI. Yue 2 writes an ABC music notation score before generating audio, which means you can edit the melody and chords and regenerate. It generates full songs with vocals and accompaniment at 48kHz stereo, supports English, Mandarin, Japanese, and Korean, and a 3.6-minute song takes about 71 seconds on an RTX 4090. The GGUF quantized version from audio-cpp runs on 8-9GB VRAM, so a 4070 or 3080 can get in on this. We walk through the ComfyUI workflow with all nodes connected, the cover mode using SheetSage2 transcription, and how to get started locally. If you work with AI music generation, want to try an open-source Suno alternative, or just want full control over your music output with editable scores, this is the model to try. No subscription, no API, runs entirely on your local GPU. Resources: YuR2 Comfy Workflow Freebies : https://www.patreon.com/aifuturetech/posts/169485916?utm_source=youtube&utm_medium=video&utm_campaign=202609 - Yue 2 Model: https://huggingface.co/m-a-p/YuE2-3B - ComfyUI Pack: https://huggingface.co/Comfy-Org/YuE2 - GGUF (low VRAM): https://huggingface.co/audio-cpp/Yue2-3B-GGUF - Demo Page: https://map-yue2.github.io/ - GitHub: https://github.com/multimodal-art-projection/YuE - Paper: https://arxiv.org/abs/2503.08638 If You Like tutorial like this, You Can Support Our Work In Patreon: https://www.patreon.com/c/aifuturetech #AImusic #ComfyUI #Yue2 #SunoAlternative #AIaudio

Comments

No comments found for this post.