ComfyUI > Nodes > Audio Separation (Demix)

ComfyUI Extension: Audio Separation (Demix)

Repo Name

AudioSeparation

Author
set-soft (Account age: 3460 days)
Nodes
View all nodes(6)
Latest Updated
2026-02-11
Github Stars
0.02K

How to Install Audio Separation (Demix)

Install this extension via the ComfyUI Manager by searching for Audio Separation (Demix)
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter Audio Separation (Demix) in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Audio Separation (Demix) Description

Audio Separation (Demix) uses MDX-Net and Demucs to separate audio into vocals, instruments, bass, drums, and experimental piano/guitar. It supports batch processing, resampling, and offers high quality or speed options.

AudioSeparation Introduction

AudioSeparation is an innovative tool designed to help you separate different audio components from a single audio file. Whether you're an AI artist looking to isolate vocals for a remix or a musician wanting to extract instrumental tracks for karaoke, AudioSeparation provides a user-friendly solution. By leveraging advanced neural networks, this extension can demix audio into distinct elements such as vocals, instruments, drums, and bass, offering you the flexibility to manipulate audio tracks as needed.

How AudioSeparation Works

AudioSeparation operates by using sophisticated neural network models to analyze and separate audio tracks. Imagine your audio file as a layered cake, where each layer represents a different sound component. AudioSeparation slices through these layers, allowing you to access each one individually. It uses two main types of models: MDX Net and Demucs. MDX Net is efficient and lightweight, making it ideal for quick tasks, while Demucs offers higher quality separation, perfect for more detailed audio work.

AudioSeparation Features

AudioSeparation is packed with features designed to make audio separation as seamless as possible:

  • Multiple Stems Support: Separate audio into multiple components like vocals, instruments, drums, and bass.
  • User-Friendly Interface: Easy to use, with clear download progress and destination paths.
  • Versatile Input Formats: Supports all audio formats, whether mono or stereo, and any sample rate.
  • Quality Options: Choose between efficient MDX models or higher quality Demucs models based on your needs.
  • Customizable Settings: Adjust settings such as segment processing and device targeting to optimize performance.

AudioSeparation Models

AudioSeparation supports a variety of models, each suited for different tasks:

  • MDX Models: These are smaller and efficient, ranging from 21 MB to 65 MB. They are perfect for quick separations and are specialized for different audio stems.
  • Demucs Models: Larger in size (84 MB to 870 MB) but offer superior quality. They support up to 4 stems and are ideal for detailed audio separation tasks.
  • Karaoke Models: These models are designed to retain secondary vocals along with instruments, providing a unique separation experience.

Troubleshooting AudioSeparation

Encountering issues? Here are some common problems and solutions:

  • Model Download Issues: If models aren't downloading, ensure your internet connection is stable. You can manually download models from here.
  • Audio Quality Concerns: Ensure your input audio is at a 44.1 kHz sample rate for optimal results. The tool will automatically adjust the sample rate if needed.
  • Performance Problems: If the tool is running slowly, try reducing the number of segments processed at once or switch to a more efficient model.

Learn More about AudioSeparation

To further enhance your experience with AudioSeparation, explore these resources:

  • Tutorials and Documentation: Visit the official documentation for detailed guides and examples.
  • Community Forums: Join discussions and seek support from other users in community forums dedicated to audio processing and AI art.
  • Example Workflows: Check out example workflows available in the ComfyUI workflow templates under the audio-separation section for practical applications of the tool. By understanding and utilizing these features and resources, you can maximize the potential of AudioSeparation in your creative projects.

Audio Separation (Demix) Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Audio Separation (Demix) detailed guide | ComfyUI