This update includes:

• Improved README
• Added more information during setup
• Changed default backend to Remote -> Hugging Face, avoiding default behavior of heavy local models that may not work on most machines
• Heavy tools (LLaMA-Mesh, hyper3d) no longer block Blender main thread

Installation

Windows/Mac/Linux (CPU)

This version is slow for running local models, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2+

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip

Windows/Linux (NVIDIA GPU)

This version is much faster for running local models, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2+

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip

Setup

Once installed, follow instructions in Setup.

This major release adds AI Agents to Blender.

• Use a variety of blender tools, similar to blender-mcp
• Supports arbitrary model backends:
  • Local (llama_cpp_python, ollama)
  • HF Inference API
  • Anthropic API
  • OpenAI API
• Adds optional integrations:
  • LLaMA-Mesh for local mesh generation and understanding
  • Hyper3D (Rodin) API for generating complex objects

Installation

Windows/Mac/Linux (CPU)

This version is slow for running local models, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2+

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip
• In addon preferences, click Download Recommended Model

Windows/Linux (NVIDIA GPU)

This version is much faster for running local models, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2+

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip
• In addon preferences, click Download Recommended Model

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Enter a prompt, for example: Create a snowman
• Click Submit

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This update includes a major backend and UI overhaul

• Now supports multiple backends, remote litellm backend for various provides
• Improved overall UI/UX

Installation

Windows/Mac/Linux (CPU)

This version is slow, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2+

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip
• In addon preferences, click Download Recommended Model

Windows/Linux (NVIDIA GPU)

This version is much faster, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2+

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip
• In addon preferences, click Download Recommended Model

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This release massively simplifies dependency management by using included wheels.

As a result, the ollama backend option is removed. A more flexible solution for using various models/backends will be added. For now, if using an ollama backend, a previous release is recommended.

Installation

Windows/Mac/Linux (CPU)

This version is slow, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2+

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip
• In addon preferences, click Download Required Models

Windows/Linux (NVIDIA GPU)

This version is much faster, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2+

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip
• In addon preferences, click Download Required Models

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This release migrates to the new Blender extension system, for Blender 4.2+.

Before installing, uninstall any previous release, then restart Blender.

Installation

Windows/Mac/Linux (CPU)

This version is slow, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2+

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip
• In addon preferences, click Download Required Models

Windows/Linux (NVIDIA GPU)

This version is much faster, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2+

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip
• In addon preferences, click Download Required Models

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This release includes support for Ollama server and additional release architectures.

Thanks to:

• @AidanNelson for adding Ollama server support #13
• @zosman1 for adding more release architectures #15

Before installing, uninstall any previous release, then restart Blender.

Installation

Windows/Mac/Linux (CPU)

This version is slow, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2

Steps

• Download meshgen-cpu-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu-{platform}.zip
• In addon preferences, click Download Required Models

Windows/Linux (NVIDIA GPU)

This version is much faster, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2

Steps

• Download meshgen-cuda-{platform}.zip in Assets below, depending on your platform
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda-{platform}.zip
• In addon preferences, click Download Required Models

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This release dramatically improves performance and memory requirements. It does so by replacing the transformers backend and full model with a llama-cpp-python backend and quantized model.

Before installing, uninstall any previous release, then restart Blender.

Installation

Windows/Mac/Linux (CPU)

This version is slow, but supports more devices. If you meet the requirements, the GPU version is recommended.

Requirements

• Blender 4.2

Steps

• Download meshgen-cpu.zip in Assets below
• In Blender, go to Edit -> Preferences -> Add-ons -> Click the arrow in the top right then Install from Disk
• Choose meshgen-cpu.zip
• In addon preferences, click Download Required Models

Windows/Linux (NVIDIA GPU)

This version is much faster, but requires a high-end NVIDIA GPU.

Requirements

• An NVIDIA GPU with at least 8GB VRAM
• CUDA 12.1
• Blender 4.2

Steps

• Download meshgen-cuda.zip in Assets below
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen-cuda.zip
• In addon preferences, click Download Required Models

Usage

• Press N -> MeshGen (or View -> Sidebar -> Select the MeshGen tab)
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues

This initial release contains a minimal integration of LLaMa-Mesh in Blender.

Installation

Windows/Linux

Requirements

• An NVIDIA GPU with at least 16GB VRAM
• CUDA 12.1
• Blender 4.2
• [7-Zip] (https://7-zip.org/download.html)

Steps

• Download meshgen-win-linux-cuda.7z in Assets below
• Right click -> Show more options -> 7-Zip -> Extract Here to extract the meshgen.zip file
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen.zip

Mac (untested)

Requirements

• Blender 4.2

Steps

• Download meshgen-macos-arm.zip in Assets below
• Extract the contained meshgen.zip file
• In Blender, go to Edit -> Preferences -> Add-ons -> Click arrow in the top right then Install from Disk
• Choose meshgen.zip

Setup

• In MeshGen addon preferences, click Download Required Models
• If set up correctly, addon preferences should display the message `Ready to generate. Press 'N' -> MeshGen to get started.'

Usage

• Press N -> MeshGen
• Click Load Generator (this will take a while)
• Enter a prompt, for example: Create a 3D obj file using the following description: a desk
• Click Generate Mesh

Troubleshooting

• Find errors in the console:
  • Windows: In Blender, go to Window -> Toggle System Console
  • Mac/Linux: Launch Blender from the terminal
• Report errors in Issues