VisoMaster-Fusion

🚀 Quick Start

Most users should use the portable launcher:

1. Create a new folder where you want VisoMaster Fusion to live.
2. Download only Start_Portable.bat from latest release.
3. Put Start_Portable.bat in the new folder and run it.

The first launch downloads the portable runtime, dependencies, FFmpeg, and model files. After setup, always start VisoMaster Fusion with Start_Portable.bat.

---

💻 System Requirements

• Operating system: Windows 10 or Windows 11, 64-bit
• GPU: Nvidia GPU recommended
• VRAM: 6 GB minimum for basic use; 8-12 GB or more recommended for heavier workflows
• Driver: Nvidia driver >=576.57 recommended for CUDA 12.9 support
• Internet: Required on first run to download dependencies and models
• Disk space: 20-30 GB free space recommended

The app can run on CPU, but AI processing is much slower. Most users should use the portable version unless they specifically want a manual development setup.

---

🧰 Non-Portable Installation

Use this path only if you want to manage the Python environment yourself.

1. Clone the repository

git clone https://github.com/VisoMasterFusion/VisoMaster-Fusion
cd VisoMaster-Fusion

Most users should use the main branch. The dev branch contains newer or in-progress changes.

2. Create and activate a Python environment

Using Anaconda:

conda create -n visomaster python=3.12 -y
conda activate visomaster
pip install uv

Using uv directly:

uv venv --python 3.12
.venv\Scripts\activate

3. Install requirements

uv pip install -r requirements_cu13.txt

4. Download required models

python download_models.py

5. Install FFmpeg

On Windows, either:

• Run: winget install -e --id Gyan.FFmpeg --version 7.1.1
• Or download https://www.gyan.dev/ffmpeg/builds/packages/ffmpeg-7.1.1-essentials_build.zip, unzip it, and add \<unzipped ffmpeg path>\bin to your Windows PATH

6. Run the application

Open Start.bat on Windows, or activate your environment in a terminal inside the VisoMaster-Fusion directory and run:

python main.py

To update a non-portable checkout:

git pull
uv pip install -r requirements_cu13.txt
python download_models.py