mcpField
T
TRELLIS Blender Plugin

TRELLIS Blender Plugin

Local
github.com/FishWoWaterDeveloper Tools77Updated 43w ago
Repository

About TRELLIS Blender Plugin

TRELLIS Blender Plugin is a Blender add-on that connects to TRELLIS and TRELLIS.2 for 3D generation from text or single images. It sends requests to an API backend and can also run as an MCP server for clients such as Claude, Cursor and Windsurf.

Key features

  1. 01Text-to-3D generation of textured meshes
  2. 02Image-to-3D generation from a single RGB image
  3. 03Texture generation for existing meshes from text or image
  4. 04Switchable TRELLIS and TRELLIS.2 backends
  5. 05Generated models imported directly into the Blender scene
  6. 06Built-in MCP server start option

Use cases

  1. 01Creating 3D model prototypes in Blender from text or images
  2. 02Adding texture detail to meshes already in a scene
  3. 03Driving 3D generation from an MCP client conversation

MCP support

The plugin can start an MCP server (trellis-mcp) so that MCP clients such as Claude, Cursor and Windsurf can invoke its 3D generation features.

#plugin#blender#mcp#trellis#generative-model#image-to-3d#aigc#text-to-3d#mcp-server#3daigc

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "trellis_blender": {
      "command": "uvx",
      "args": [
        "trellis-mcp"
      ]
    }
  }
}
Run commanduvx trellis-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypitrellis-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

TRELLIS & TRELLIS.2 Blender Addon

Update: add support for TRELLIS.2

A Blender addon that integrates the 3D generation capabilities of TRELLIS and TRELLIS2 into blender.

DemoVideo

Features

TRELLIS
  • Text-to-3D: native generation of textured 3D mesh from text
  • Image-to-3D: native generation of textured 3D mesh from a single RGB image
  • Text-conditioned Detail Variation: generating textures for a mesh given text
  • Image-conditioned Detail Variation: generating textures for a mesh given a single RGB image
TRELLIS2
  • Text-to-3D: generation of textured 3D mesh from text (t2i using z-image-turbo, and then image2mesh using trellis.2)
  • Image-to-3D: native generation of textured 3D mesh from a single RGB image (native trellis.2)
MCP integration

Integrates with MCP and can communicate with Cursor/Windsurf. Refer to Trellis MCP

Installation

Requirements

You can also start both servers and switch the backend in the blender addon.

Enable the plugin
  1. Download the plugin files (clone this repo)
  2. In Blender, go to Edit > Preferences > Add-ons
  3. Click "Install" and select the trellis_for_blender.py file
  4. Enable the addon by checking the box next to "3D View: TRELLIS"
Native Workflow
  1. Access the panel (open 3d viewport and press n to open sidebar), find TRELLIS.
  2. (Optionally) Select an object in the scene, select an image as conditional input.
  3. Adjust generation parameters (empirically can use fewer steps)
  4. The plugin will upload both the object(if selected) and the image/text to the API backend.
  5. When finished, the model can be downloaded and imported into the scene.

You can see the historical requests in the main panel

MCP Workflow
  1. Access the panel (open 3d viewport and press n to open sidebar), find TRELLIS, click Start MCP Server
  2. Open Claude/Cursor/Windsurf, paste following configuration:
"mcpServers": {
        "trellis": {
            "command": "uvx",
            "args": [
                "trellis-mcp"
            ]
        }
    }

Generation Parameters

  • Sparse Structure Settings
    • Sample Steps (sampling steps for structure diffusion, by default 12)
    • CFG Strength (classifier-free-guidance, by default 7.5, higher value will better align the input image)
  • Structured Latent Settings
    • Sample Steps (sampling steps for SLAT diffusion, by default 12)
    • CFG Strength (classifier-free-guidance, by default 7.5, higher value will better align the input image)
  • Postprocessing Mesh Options
    • Simplify Ratio (# of triangles to remove, by default 0.95)
    • Texture Size (by default 1024, can set to 2048 for higher quality, but slower)
    • Texture Bake Mode ('fast' or 'opt', 'opt' can be slow but has higher quality)

Any issue/discussion/contribution is welcomed!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.