ComfyUI Node: Instrumental using MDX

Authored by set-soft

Created

Updated

29 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

audio/separation

Inputs

input_sound AUDIO
model
  • ⬇️ Kim Jensen
  • ⬇️ UVR 1
  • ⬇️ UVR 187 beta
  • ⬇️ UVR 2
  • ⬇️ UVR 292 Full
  • ⬇️ UVR 3
  • ⬇️ UVR 82 beta
  • ⬇️ UVR 90 beta
  • ⬇️ UVR HQ 1
  • ⬇️ UVR HQ 2
  • ⬇️ UVR HQ 3
  • ⬇️ UVR HQ 4
  • ⬇️ UVR HQ 5
  • ⬇️ UVR Karaoke
  • ⬇️ UVR Main
segments INT
target_device
  • cpu

Outputs

AUDIO

AUDIO

Extension: Audio Separation (Demix)

Audio separation (aka demixing) nodes, for Vocals, Instruments, Bass, Drums and Others (experimental Piano and Guitar). Using MDX-Net and Demucs, no extra dependencies, support for batch and resample. Choose between High Quality and Speed. All safetensor models (No ONNX, No PyTorch)

Authored by set-soft

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more