ComfyUI > Nodes > Audio Separation (Demix) > Demucs Audio Separator

ComfyUI Node: Demucs Audio Separator

Class Name

AudioSeparateDemucs

Category
audio/separation
Author
set-soft (Account age: 3460days)
Extension
Audio Separation (Demix)
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

Demucs Audio Separator Description

AudioSeparateDemucs isolates audio components like vocals and instruments using Demucs model.

Demucs Audio Separator:

AudioSeparateDemucs is a powerful node designed to separate audio tracks into distinct components using advanced machine learning techniques. This node leverages the Demucs model, a state-of-the-art deep learning architecture, to isolate different audio elements such as vocals, instruments, and other sound components from a mixed audio track. The primary benefit of using AudioSeparateDemucs is its ability to produce high-quality separations, making it an invaluable tool for audio engineers, music producers, and AI artists who wish to manipulate or analyze individual audio elements. By utilizing PyTorch and torchaudio libraries, this node ensures efficient processing and high fidelity in the separated audio outputs. The main goal of AudioSeparateDemucs is to provide users with a seamless and effective way to deconstruct complex audio tracks into their constituent parts, enabling creative and technical exploration of audio content.

Demucs Audio Separator Input Parameters:

model

The model parameter specifies the deep learning model used for audio separation. It determines the architecture and weights that will be applied to the input audio to achieve separation. The choice of model can significantly impact the quality and characteristics of the separated audio. Users can select from various pre-trained models, each optimized for different types of audio content. There are no explicit minimum or maximum values, but users should ensure compatibility with the node's requirements.

mix

The mix parameter is the input audio tensor that contains the mixed audio track to be separated. This parameter is crucial as it provides the raw audio data that the model will process. The quality and format of the input audio can affect the separation results, so it is recommended to use high-quality audio files for optimal performance. The mix should be a multi-channel audio tensor, typically with a sample rate that matches the model's requirements.

sample_rate

The sample_rate parameter defines the sampling rate of the input audio. It is essential for ensuring that the audio is processed correctly by the model. The sample rate should match the rate expected by the model to avoid any discrepancies in audio processing. Common sample rates include 44.1 kHz and 48 kHz, but users should refer to the model's documentation for specific requirements.

segment

The segment parameter controls the length of audio segments processed by the model at a time. It is measured in seconds and affects how the audio is chunked during processing. A smaller segment size may lead to more precise separation but can increase processing time, while a larger segment size may speed up processing but reduce precision. The default value is typically around 10.0 seconds.

overlap

The overlap parameter specifies the amount of overlap between consecutive audio segments. It is expressed as a fraction of the segment length and helps to ensure smooth transitions between segments. Overlap can improve the continuity of the separated audio but may also increase processing time. A common default value is 0.1, representing 10% overlap.

device

The device parameter indicates the computing device used for processing, such as a CPU or GPU. This parameter is crucial for optimizing performance, as using a GPU can significantly accelerate processing times compared to a CPU. Users should select the device that best matches their hardware capabilities and processing needs.

chunk_fade_shape

The chunk_fade_shape parameter determines the shape of the fade applied to the edges of audio chunks. This helps to minimize artifacts and ensure smooth transitions between segments. Common fade shapes include "linear" and "half_sine," with each offering different characteristics in terms of smoothness and artifact reduction.

Demucs Audio Separator Output Parameters:

separated_tensors

The separated_tensors output parameter contains the audio tensors resulting from the separation process. Each tensor corresponds to a distinct audio component, such as vocals or instruments, extracted from the input mix. These tensors allow users to access and manipulate individual audio elements, facilitating creative and technical applications such as remixing, analysis, or enhancement of specific audio parts.

Demucs Audio Separator Usage Tips:

  • Ensure that the input audio is of high quality and matches the sample rate expected by the model to achieve the best separation results.
  • Experiment with different models to find the one that best suits your specific audio content and separation needs.
  • Adjust the segment and overlap parameters to balance processing time and separation precision according to your requirements.

Demucs Audio Separator Common Errors and Solutions:

"AudioSplit: Input audio has only one channel."

  • Explanation: This error occurs when the input audio does not have the required number of channels for separation.
  • Solution: Ensure that the input audio is stereo or multi-channel, as the separation process requires at least two channels to function correctly.

"Model not compatible with input sample rate."

  • Explanation: This error indicates a mismatch between the input audio's sample rate and the model's expected sample rate.
  • Solution: Verify the sample rate of your input audio and ensure it matches the sample rate required by the selected model. Adjust the sample rate if necessary before processing.

Demucs Audio Separator Related Nodes

Go back to the extension to check out more related nodes.
Audio Separation (Demix)
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.

Demucs Audio Separator