awesome-repositories.com
Blog
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektÜber unsRanking-MethodikPresseMCP-Server
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
MrForExample avatar

MrForExample/ComfyUI-3D-Pack

0
View on GitHub↗
3,648 Stars·360 Forks·Python·mit·11 Aufrufe

ComfyUI 3D Pack

ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts.

The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source.

The toolset covers 3D asset rendering and scene rendering by simulating camera perspectives and lighting to produce 2D imagery from meshes and Gaussian splats. Additional capabilities include the generation of normal maps and multi-view mesh reconstruction to refine surface details and geometry.

Features

  • 3D Asset Generators - Provides a suite of tools to synthesize textured 3D meshes and models from images or text prompts.
  • Depth Estimation - Provides neural network-based depth estimation from single images to seed 3D mesh generation.
  • Node-Based Generative Pipelines - Orchestrates 3D generation workflows through a modular, node-based visual graph of operations.
  • Multi-View Image Generations - Produces consistent sets of multi-view images from a single prompt to facilitate 3D reconstruction.
  • Multi-View Image Generators - Produces consistent sets of multi-view images from single prompts to facilitate 3D reconstruction.
  • 3D Reconstruction - Converts 2D images and depth maps into three-dimensional meshes and surface geometries.
  • Gaussian Splatting - Represents 3D scenes as collections of learned 3D Gaussians for high-fidelity volumetric rendering.
  • Gaussian Splat Rendering - Renders 2D imagery from 3D meshes and Gaussian splats by simulating camera perspectives and lighting.
  • Multi View Reconstruction - Generates 3D geometry by calculating depth and surface normals across multiple consistent camera perspectives.
  • ComfyUI Custom Node Suites - Provides a comprehensive set of custom nodes for ComfyUI to enable 3D generation and rendering workflows.
  • Image-to-3D Texture Engines - Produces 3D meshes with RGB textures derived from multi-view images, reference images, or text prompts.
  • 3D Scene Renderers - Creates 2D images from 3D assets by simulating specific camera angles and lighting environments.
  • Image-to-Mesh Generation - Builds three-dimensional polygonal meshes directly from single two-dimensional image inputs.
  • Gaussian Splatting - Generates volumetric 3D representations from multi-view images or transformer models for high-fidelity scene rendering.
  • Textured Mesh Rendering - Renders 2D imagery from 3D meshes and Gaussian splats using simulated camera perspectives.
  • Volumetric Mesh Extraction - Converts volumetric data and point clouds into polygonal triangle meshes for use in 3D software.
  • Generative Texture Mappers - Utilizes generative models to project 2D image data onto 3D geometry as realistic surface textures.
  • Normal Map Extractions - Extracts high-resolution normal maps from images to refine the surface detail of generated 3D models.

Star-Verlauf

Star-Verlauf für mrforexample/comfyui-3d-packStar-Verlauf für mrforexample/comfyui-3d-pack

KI-Suche

Entdecke weitere awesome Repositories

Beschreibe in einfachen Worten, was du brauchst — die KI bewertet tausende kuratierte Open-Source-Projekte nach Relevanz.

Start searching with AI

Häufig gestellte Fragen

Was macht mrforexample/comfyui-3d-pack?

ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts.

Was sind die Hauptfunktionen von mrforexample/comfyui-3d-pack?

Die Hauptfunktionen von mrforexample/comfyui-3d-pack sind: 3D Asset Generators, Depth Estimation, Node-Based Generative Pipelines, Multi-View Image Generations, Multi-View Image Generators, 3D Reconstruction, Gaussian Splatting, Gaussian Splat Rendering.

Welche Open-Source-Alternativen gibt es zu mrforexample/comfyui-3d-pack?

Open-Source-Alternativen zu mrforexample/comfyui-3d-pack sind unter anderem: tencentarc/instantmesh — InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large… xxlong0/wonder3d — Wonder3D is a diffusion-based system for single image 3D reconstruction. It generates high-detail 3D meshes from a… ashawkey/stable-dreamfusion — This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language… nerfstudio-project/gsplat — gsplat is a high-performance differentiable rasterization engine for 3D Gaussian splatting, designed for real-time… carson-katri/dream-textures — Dream Textures is a Stable Diffusion integration for Blender that provides tools for text-to-image generation, depth… facebookresearch/pifuhd — pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D…

Open-Source-Alternativen zu ComfyUI 3D Pack

Ähnliche Open-Source-Projekte, sortiert nach der Anzahl der gemeinsamen Funktionen mit ComfyUI 3D Pack.
  • tencentarc/instantmeshAvatar von TencentARC

    TencentARC/InstantMesh

    4,431Auf GitHub ansehen↗

    InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large reconstruction model to convert a single two-dimensional image into a three-dimensional object mesh. The system functions as a textured 3D mesh exporter, saving generated objects with either vertex colors or full texture maps for use in external rendering software. The framework covers a range of capabilities including feed-forward geometry inference, single-image depth estimation, and neural radiance fields. It also supports differentiable mesh rendering and workflows for spars

    Python
    Auf GitHub ansehen↗4,431
  • xxlong0/wonder3dAvatar von xxlong0

    xxlong0/Wonder3D

    5,388Auf GitHub ansehen↗

    Wonder3D is a diffusion-based system for single image 3D reconstruction. It generates high-detail 3D meshes from a single input image by producing consistent multi-view normal maps and color images. The pipeline functions as a multi-view normal map generator and a textured mesh extractor. It uses cross-domain multi-view synthesis to create view-dependent maps, which are then converted into 3D geometry through radiance fusion and memory-efficient surface reconstruction. The project covers 3D mesh generation, multi-view generation, and textured 3D modeling. It also includes capabilities for tr

    Python3d-aigc3d-generation3dgeneration
    Auf GitHub ansehen↗5,388
  • ashawkey/stable-dreamfusionAvatar von ashawkey

    ashawkey/stable-dreamfusion

    8,841Auf GitHub ansehen↗

    This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language descriptions or two-dimensional images into three-dimensional assets using neural radiance fields and diffusion models. The system utilizes score-distillation sampling and diffusion-based guidance to refine 3D shapes without requiring 3D training data. It includes specialized tools for transforming neural representations into exportable meshes with texture and material data, as well as a pipeline for iterative optimization of geometry and textures. The project covers a broad r

    Python
    Auf GitHub ansehen↗8,841
  • nerfstudio-project/gsplatAvatar von nerfstudio-project

    nerfstudio-project/gsplat

    4,528Auf GitHub ansehen↗

    gsplat is a high-performance differentiable rasterization engine for 3D Gaussian splatting, designed for real-time novel view synthesis from 2D images. It provides a complete pipeline for reconstructing 3D scenes by optimizing differentiable Gaussian representations, training models from COLMAP-processed captures or proprietary device files, and generating new viewpoints through a CUDA-accelerated rendering backend. The framework distinguishes itself through memory-optimized CUDA kernels that reduce training memory usage by up to 4x compared to standard implementations while matching publishe

    Pythongaussian-splatting
    Auf GitHub ansehen↗4,528
  • Alle 30 Alternativen zu ComfyUI 3D Pack anzeigen→