Wan2GP (WanGP)

by DeepBeepMeep

An all-in-one app to run big video models (Wan, LTX…) on modest graphics cards.

10.3 k stars GitHub WanGP Community License 2.0 Free when localLocal

View on GitHub →

What it does

Aggressive memory optimizations: some models run with 6 GB VRAM
Video, image and audio in one local web UI, with a job queue
Automatically downloads model files suited to your hardware

Install it

Requirements: Git, Conda (Python 3.11), recent NVIDIA driver; Triton as well on Windows.

Clone the repository

git clone https://github.com/deepbeepmeep/Wan2GP.git

Create the environment

cd Wan2GP && conda create -n wan2gp python=3.11.14 && conda activate wan2gp

Install PyTorch

pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 --index-url https://download.pytorch.org/whl/cu130

Install dependencies

pip install -r requirements.txt

Run

python wgp.py

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install Wan2GP (WanGP) (https://github.com/deepbeepmeep/Wan2GP) on my machine.
1. Check the requirements: Git, Conda (Python 3.11), recent NVIDIA driver; Triton as well on Windows. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Clone the repository: git clone https://github.com/deepbeepmeep/Wan2GP.git
- Create the environment: cd Wan2GP && conda create -n wan2gp python=3.11.14 && conda activate wan2gp
- Install PyTorch: pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 --index-url https://download.pytorch.org/whl/cu130
- Install dependencies: pip install -r requirements.txt
- Run: python wgp.py
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.