Generative AI for video, image & audio—on your GPU.

WanGP is a free, open-source workspace for running generative video, image, audio and text-to-speech models locally. It combines model selection, prompting, queues, galleries, LoRAs, preprocessing and post-processing in one browser-based interface.

Yes. Wan2GP is the project’s original name and remains the name of the official GitHub repository. WanGP is the current product name. Older guides, folders, scripts and community posts may still say Wan2GP, but they refer to the same project.

WanGP is free to install and run locally, including for internal company use. The official project will never ask for a license fee, subscription or donation simply to run WanGP on your own computer. Paid hosting, SaaS, white-labeling and other restricted commercialization require separate permission; model and third-party component licenses also continue to apply. Read the WanGP Community License 2.0

Select smaller models can run with as little as 6 GB of VRAM. Larger models, higher resolutions and longer videos require more. The practical requirement depends on the chosen model, quantization, memory profile, frame count and resolution—so start with a recommended low-VRAM model and scale up.

WanGP supports NVIDIA GTX 10-series, RTX 20-series and newer GPUs, with generation options tailored to each generation. AMD support covers several RDNA 2, RDNA 3, RDNA 3.5 and RDNA 4 families; follow the dedicated AMD guide because setup and compatibility vary by GPU architecture and operating system.

Choose one of three paths. First: the scripts in the official GitHub repository for the most direct, project-maintained setup on Windows, Linux or macOS. Second: Pinokio for a graphical app-manager workflow. Third: Wan2GP Desktop for an all-in-one Windows launcher with hardware detection and maintenance tools.

No. The application fetches the files needed by the models you choose, and the first use of a model can involve a substantial download. Keep enough disk space available and let the first download finish before diagnosing a stalled model load.

Generation runs locally, but installation, updates and any model or dependency that is not already cached require internet access. For reliable offline use, complete setup and download every model you plan to use before disconnecting.

Reduce resolution or frame count, choose a smaller or quantized model, lower the batch size, and use a more memory-efficient WanGP profile. Closing GPU-accelerated apps also helps. The repository includes scripts that launch Chrome without GPU acceleration, which can return additional VRAM to WanGP.

Speed depends on the model, GPU, attention backend, quantization, memory profile, resolution and number of steps. Use the hardware-appropriate installer settings first. Optional accelerators such as Triton and SageAttention can help on compatible GPUs; the official installation guide documents the supported combinations.

Keep using the same path you installed with. Official-script installations use scripts/update.bat on Windows or scripts/update.sh on Linux/macOS. Pinokio installations update through Pinokio. Wan2GP Desktop installations use the launcher’s built-in maintenance tools.

Join the official Discord community for setup help, workflow ideas and sharing generations. For reproducible bugs, search existing GitHub issues first and open a new issue with your operating system, GPU, VRAM, installation method, model, settings and terminal error.