PozzettiAndrea/ComfyUI-TRELLIS2

ComfyUI wrapper for Trellis 2

What it solves

It enables the generation of high-quality 3D meshes with Physically Based Rendering (PBR) materials from a single 2D image, integrating Microsoft's TRELLIS.2 model into the ComfyUI node-based interface.

How it works

The project provides a set of custom nodes for ComfyUI that wrap the TRELLIS.2 image-to-3D generation model. This allows users to build visual workflows to transform images into 3D assets.

Who it’s for

3D artists, developers, and AI enthusiasts using ComfyUI who want to create 3D models from images.

Highlights

  • High-quality 3D mesh generation
  • Support for PBR (Physically Based Rendering) materials
  • Single-image input for 3D creation
  • Integration with the ComfyUI ecosystem

Related

  • Project
    visualbruno/ComfyUI-Trellis2

    ComfyUI‑Trellis2 is a custom‑node pack that integrates Microsoft’s TRELLIS.2 3‑D diffusion pipeline into the visual ComfyUI interface. It adds multi‑view generation, voxel‑to‑mesh conversion, texture mapping, and a suite of geometry‑processing nodes (smoothing, hole‑filling, simplification, etc.). The repo supplies Windows wheels for required C++ extensions, detailed installation steps, and example workflows, enabling users to turn images into textured 3‑D meshes directly within ComfyUI.

  • Project
    visualbruno/ComfyUI-Hunyuan3d-2-1

    A ComfyUI wrapper for Tencent's Hunyuan3D-2.1 model that enables the generation of textured 3D models within a visual node-based workflow.

  • Project
    sakalond/StableGen

    An open-source Blender addon that enables AI-powered 3D mesh generation from images/text and advanced AI texturing for 3D models using a ComfyUI backend.

  • Project
    melMass/comfy_mtb

    A collection of custom nodes for ComfyUI that extends the image generation workflow with additional utility tools.

  • Project
    heshengtao/comfyui_LLM_party

    A comprehensive set of ComfyUI nodes for building LLM workflows, enabling the integration of AI agents, RAG, and VLMs into visual image generation pipelines.