https://github.com/christian-byrne/audio-separation-nodes-comfyui
Separate stems (vocals, bass, drums, other) from audio. Recombine, tempo match, slice/crop audio
https://github.com/christian-byrne/audio-separation-nodes-comfyui
comfyui comfyui-nodes
Last synced: 13 days ago
JSON representation
Separate stems (vocals, bass, drums, other) from audio. Recombine, tempo match, slice/crop audio
- Host: GitHub
- URL: https://github.com/christian-byrne/audio-separation-nodes-comfyui
- Owner: christian-byrne
- Created: 2024-07-03T08:01:04.000Z (10 months ago)
- Default Branch: master
- Last Pushed: 2025-01-05T19:12:48.000Z (3 months ago)
- Last Synced: 2025-03-28T19:05:36.890Z (20 days ago)
- Topics: comfyui, comfyui-nodes
- Language: Python
- Homepage:
- Size: 100 MB
- Stars: 197
- Watchers: 3
- Forks: 15
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-comfyui - **audio-separation-nodes-comfyui**
README
https://github.com/user-attachments/assets/c5cf20de-a17f-438d-81ac-0c392af669cf
# Examples
#### _`Separating Voices in a Video`_
Show
> [!NOTE]
>
> In order to load videos into the LoadAudio Node, change [this line](https://github.com/comfyanonymous/ComfyUI/blob/faa57430b0ff882275b1afcf6610e8e9f8a5929b/comfy_extras/nodes_audio.py#L185) in your Comfy install to include the video's extension (e.g., `.mp4`)
[workflow.json](./example_workflows/Isolate%20Vocals%20from%20Video.json)
https://github.com/user-attachments/assets/c5af418e-7137-4c36-b86e-3352cf558ea8
#### _`Replacing BGM with StableAudio-Generated BGM`_
Show
> [!NOTE]
>
> In order to load videos into the LoadAudio Node, change [this line](https://github.com/comfyanonymous/ComfyUI/blob/faa57430b0ff882275b1afcf6610e8e9f8a5929b/comfy_extras/nodes_audio.py#L185) in your Comfy install to include the video's extension (e.g., `.mp4`)
You can use this to replace copyrighted BGM in a video with new BGM. You can set the denoise low, so that the new BGM is still stimilar to the original.
[workflow json](./example_workflows/Replace%20BGM%20with%20Stable-Audio-Generated%20Music.json)
https://github.com/user-attachments/assets/a7d5656b-5f8b-439a-936f-6ebb6a0d538a
#### _`Remixing Songs with StableAudio`_
Show
- [workflow json](./example_workflows/Remix%20Song.json)
- [example output (audio file) with embedded workflow](https://github.com/christian-byrne/audio-separation-nodes-comfyui/raw/refs/heads/demo-files/wiki/examples/ComfyUI_temp_iaepj_00001_.flac)
- [example output (audio file) with embedded workflow](https://github.com/christian-byrne/audio-separation-nodes-comfyui/raw/refs/heads/demo-files/wiki/examples/ComfyUI_00002_.flac)
#### _`Separating Song Vocals`_
Show
[workflow.json](./example_workflows/Isolate%20Vocals%20from%20Audio.json)
https://github.com/user-attachments/assets/c5cf20de-a17f-438d-81ac-0c392af669cf
#### _`Extracting Instrumentals from Songs`_
Show
- [workflow json](./example_workflows/Extract%20Instrumental%20from%20Song.json)
# Requirements
```m
librosa==0.10.2
torchaudio>=2.3.0
numpy
moviepy
```
# Installation
1. If you run ComfyUI inside of a virtual environment, make sure it is activated
1. `git clone` this repository in `ComfyUI/custom_nodes` folder
1. `cd` into the cloned repository
1. `pip install -r requirements.txt`