Hunyuan3D-2 Windows Portable

English | 中文说明

A dedicated package for running Hunyuan3D 2.0 Gradio Web App (official demo) on Windows.

How to Use - Generate Shape Only

The simplest way to experience Hunyuan3D-2. Input an image, and you’ll get a 3D model (white mesh).

1. Requirements:

   • NVIDIA GPU with at least 6GB of VRAM (4GB may work but will be very slow).

   • GPU driver version must be newer than March 2024 (version >550).

2. Download Hunyuan3D2_WinPortable.7z, and extract it to a convenient location.

3. Run 2-download-models.bat and wait for the download to complete (~26GB).

4. Run 3-run.bat, ignore error messages about EP Error. Wait for the info message:

   Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)

5. Open http://localhost:8080/ in your browser. Enjoy!

6. Output files will be saved in Hunyuan3D-2\gradio_cache.

Other options:

• If your GPU has less than 6GB VRAM, use run-very_low_vram.bat.

How to Use - Generate Shape and Texture

Generating textures requires a few additional steps.

1. Requirements:

   • NVIDIA GPU with at least 8GB of VRAM (6GB may work but will be very slow).

   • GPU driver version must be newer than March 2024 (version >550).

   • Minimum 24GB of system RAM.

2. Install CUDA Toolkit 12.4.1.

   • Only Libraries and Compilers are needed to install.

3. Install Visual Studio Build Tools 2022 ( Page | EXE ).

   • During setup, select the "Desktop development with C++" workload.

4. Download and extract Hunyuan3D2_WinPortable.7z. Or check for newer versions at releases page.

5. Run update.bat to ensure you have the latest code.

6. Run 1-compile-install-texture-gen.bat, wait for the installation to finish.

7. Run 2-download-models.bat to download necessary models (~26GB).

8. Run 3-run.bat. When ready, the following message will appear:

   Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)

   • If you see EP Error: Can’t load TensorRT, the app will automatically fallback to CUDA. This error can be safely ignored.

9. Open http://localhost:8080/ in your browser.

10. Output files will be saved in Hunyuan3D-2\gradio_cache.

Other options:

• Use run-very_low_vram.bat if your GPU has less than 8GB VRAM.

How to use - Text to 3D

The Text to 3D feature combines: (1) Text to Image (2) Image to 3D. For an experienced user, it might not be worth downloading another Text-to-Image model. So this feature is disabled by default.

But if you want to (the HunyuanDiT model works great), you can have it enabled once 2-download-models.bat is complete, no matter Texture Generation is enabled or not.

Run run-with-text_to_3d.bat. This will download the required models (~13.4GB) and start the app. If download fails, just run the script again.

Tips

1. The "Remove Background" feature uses rembg with default settings, which may leave faint white edges. Turn it off if your images already have clean alpha channels.

2. I have 24GB VRAM! Let the app use more!

   • Edit run-very_low_vram.bat, replace --profile 5 with --profile 1.

   • Beneath this argument, is the Hunyuan3D-2GP made by DeepBeepMeep.

   • You can find more detail about profile level on mmgp manual.

3. To update:

   • Run update.bat.

   • Note: This package uses a customized fork of Hunyuan3D 2.0, maintained by me, which might not always be up-to-date.

4. Need to set a proxy for Internet access?

   • Add the following lines on top to any script you run into issues with, adjusting for your proxy server:

set HTTP_PROXY=http://localhost:1080
set HTTPS_PROXY=http://localhost:1080

Thanks

• Special thanks to the researchers, developers, and all contributors of Hunyuan3D 2.0.

• Kudos to DeepBeepMeep for creating mmgp and Hunyuan3D-2GP, bringing Hunyuan3D 2.0 to less-capable GPUs.

More

Explore my other projects:

• Comfy3D-WinPortable - Run ComfyUI-3D-Pack on Windows.

• StableFast3D-WinPortable - Run SF3D on Windows.

• ComfyUI-Windows-Portable - A ComfyUI bundle with 40+ custom nodes.

• ComfyUI-Docker - Run ComfyUI in containers.