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.
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.
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…
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
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
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
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