Downloads
-
- Demucs GUI Download
- Demucs GUI CPU Windows 64-bit
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 226.8 MB
- File
- Signature
-
- Demucs GUI Download
- Demucs GUI CUDA, MKL Windows 64-bit
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 1.2 GB
- File
- Signature
-
- Demucs GUI Download
- Demucs GUI CPU, MPS macOS ARM64
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 264.4 MB
- File
- Signature
-
- Demucs GUI Download
- Demucs GUI CPU macOS 64-bit; MPS macOS Rosetta 2
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 364.4 MB
- File
- Signature
-
- Demucs GUI Download
- Demucs GUI Source Code - TAR GZ
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 2.2 MB
- File
- Signature
-
- Demucs GUI Download
- Demucs GUI Source Code - ZIP
- Antivirus
- 0 / 0
- Version
- 1.2b1
- Size
- 2.2 MB
- File
- Signature
# Change Log
About the files:
Demucs-GUI_1.2b1_cpu.7z: For Windows users without accelerators (e.g. GPU).
Demucs-GUI_1.2b1_cuda_mkl.7z: For Windows users with NVIDIA GPU (whose compute capability is greater than 3.5) or Intel GPU (Intel Arc & Intel Xe).
Demucs-GUI_1.2b1_macOS_x86_64_Rosetta2.dmg: For macOS users (Both Intel Mac and Apple Silicon Mac). You may need to install Rosetta 2 on Apple Silicon Mac. MPS acceleration is available on Apple Silicon Mac.
Demucs-GUI_1.2b1_macOS_ARM64.dmg: For macOS users with Apple Silicon CPU. MPS acceleration is available.
Updates
1. Supports CUDA and Intel MKL at the same time
2. Supports Intel Extension for PyTorch 2.1.30+xpu
3. Updated libraries! From this version, Demucs-GUI will be packed with Intel Extension for PyTorch 2.1.30+xpu and both NVIDIA card and Intel card can be used in a same build!
Fixes
1. Can't write to the output file when using FFMpeg encoder
2. Default mixer preset may be edited
3. Applying mixer preset will cause error
Description
Demucs GUI is a GUI for python project demucs (Demucs Music Source Separation) with optimized memory usage in CUDA.
Please read release notes on GitHub Release before using!
The project aims to let users without any coding experience separate tracks without difficulty. Since the original project Demucs used a scientific library torch,the packed binaries with the environment are massive. If you have questions about usage or the project, please open an issue on GitHub to tell us.
Note: This project includes the code of Demucs under the MIT license.
System requirements
For Windows: At least Windows 8
For Mac: At least macOS 10.15
For Linux: We currently have no intention to pack binaries for Linux.
Hardware
Memory: At least 6GB memory,but an 8GB swap may be required.At least 3GB of private memory (not shared memory) is required.The longer the track you want to separate, the more memory will be required.
GPU: Only NVIDIA GPUs are available.