YuE2 music generation lands in ComfyUI with editable piano roll and AR LoRA training
PurzBeats · x · 2026-09-15
The ComfyUI-FL-YuE2 node pack brings YuE2 music generation into ComfyUI, with training now running in Comfy via a custom node pack built on the RVQ Adapter.
Highlights:
- Compose songs from lyrics and style, build or import an ABC score, and render 48 kHz stereo audio with YuE2-3B.
- Generate music and train AR LoRAs on reviewed datasets, with checkpoint previews.
- Works with ComfyUI's standard audio nodes; installable via ComfyUI Manager and reuses the existing Torch install.
Related event: YuE2 Music Model Gets ComfyUI Nodes and LoRA Trainer(2 posts)→
More from Multimodal
- Spatial Hub aggregates ~5000 public COLMAP-compatible spatial datasets for world models — janusch_patas · 2026-10-31
- Single image to walkable 3D Gaussian splat scene using World Labs Atlas and WebGPU — XRarchitect · 2026-10-31
- 60+ community-made ChatGPT slash-style words turn one word into a full visual style — heyshrutimishra · 2026-10-31
- Cartesia's cascaded voice agents top the Speech Agent Arena, beating native speech-to-speech — rohanpaul_ai · 2026-10-31
- Hyperflow H3 hits #5 on I2V and #3 on video editing at under half Seedance 2.5's price — ArtificialAnlys · 2026-10-31
- Krea plugin brings image and video generation, sketch-to-animation into Grok — angrypenguinPNG · 2026-10-31