Open-source alternatives to TRELLIS.2

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

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 3

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

This project is a browser-based, physically based path-tracing renderer built on WebGL and integrated with Three.js. It functions as a real-time global illumination engine, calculating light bouncing, soft shadows, reflections, refractions, and color bleeding interactively within web environments. The rendering system incorporates progressive multi-pass accumulation to refine noisy images iteratively over multiple frames, alongside GPU-accelerated spatial acceleration structures and bounding volume hierarchies to handle complex geometry. It supports diverse material types such as refractive

Kajiya is a physically based rendering engine and real-time global illumination renderer. It utilizes a GPU-accelerated path tracer to simulate real-world material properties, such as roughness and metalness, to achieve photorealistic visual results. The engine incorporates a temporal super-resolution upscaler to increase final render resolution by reconstructing images from lower-resolution internal frames. It also generates high-fidelity reference images through path-tracing to verify the visual accuracy of real-time lighting outputs. The system covers 3D scene visualization and asset mana

Threestudio is a 3D generative AI framework designed to create three-dimensional assets from text prompts and images. It provides specialized pipelines for text-to-3D generation and image-to-3D reconstruction, utilizing a neural radiance field trainer to produce geometry and textures. The framework is distinguished by its support for hybrid geometry backends, including signed distance functions, tetrahedra grids, and volume grids. It employs score distillation sampling to guide the generation process and features a modular plugin system for loading custom modules and nodes. The system covers

TripoSR is a single-image 3D reconstruction system that generates a high-quality textured mesh from one photograph in under half a second. It uses a feedforward neural network to process a single image through a transformer architecture, compressing the input into a compact latent vector that conditions the entire reconstruction pipeline. The system outputs a separate UV texture map with configurable resolution, replacing vertex colors for higher-quality surface detail. The project is built around an end-to-end differentiable pipeline that trains the entire reconstruction system from image in

This project is a diffusion model training framework and image synthesis pipeline. It provides the tools necessary to train generative models to learn image data distributions through an iterative denoising process. The framework includes a generative model evaluation tool consisting of automated scripts used to measure the quality and accuracy of produced samples. The system covers model training pipelines and performance evaluation for generative diffusion models.

TRELLIS is a 3D generative AI model and latent diffusion framework designed to transform natural language descriptions or reference images into textured 3D assets. It operates as a text-to-3D asset generator that utilizes structured latent representations to produce high-quality 3D meshes, Gaussians, and Radiance Fields. The system functions as a multi-format 3D decoder, converting internal representations into standard exchange formats such as GLB and PLY. It also serves as a 3D asset editing tool, enabling the modification of specific regions of generated objects through targeted text or im

Trois is a declarative 3D scene manager and a Three.js component library for Vue 3. It acts as a reactive wrapper that maps Three.js scene graphs and materials to a Vue component tree, allowing for the creation of web-based 3D renderers using HTML-like templates. The project synchronizes a reactive component tree with a 3D scene graph through proxy-based state binding and reactive property mapping. It features a component-based scene graph that manages spatial transformations and object lifetimes, integrating a requestAnimationFrame loop with component lifecycle events. The library covers a

Shap-E is a generative 3D modeling system that creates three-dimensional digital assets from natural language descriptions or two-dimensional images. It functions as a generative model capable of producing three-dimensional implicit functions and assets. The project includes a 3D latent encoder that converts trimeshes and 3D models into latent representations using point clouds and multiview renders. It utilizes an image-to-3D generator to produce assets from synthetic view images and a text-to-3D generator to build shapes from text prompts. The system implements a pipeline involving latent

This repository is a comprehensive collection of functional 2D and 3D demo projects and implementation samples for the Godot Game Engine. It serves as an interactive tutorial and reference library, providing a working codebase to demonstrate how to apply engine features in real-world scenarios. The collection focuses on practical implementation guides, covering a wide array of technical capabilities from basic engine fundamentals to advanced rendering and scripting techniques. It allows users to study the application of node-based composition, asset pipelines, and game logic through direct ex

Assimp is a cross-platform 3D asset pipeline and import library that loads numerous industry-standard 3D file formats into a single unified internal data structure. It functions as a framework for converting 3D models between different file formats across multiple operating systems and architectures. The project provides a 3D mesh processing tool for normalizing and optimizing geometry through triangulation, vertex removal, and normal generation. It also includes a 3D asset export utility to write internal scene data back into various external file formats. The system covers broad capability

Cocos Engine is a cross-platform game engine designed for building high-performance 2D and 3D interactive experiences for web, mobile, and desktop platforms. It features a multi-backend rendering engine and a 2D and 3D physics simulator, utilizing a core architecture that combines a C++ runtime for performance with TypeScript for game logic scripting. The engine distinguishes itself through a multi-platform deployment system that packages projects for native operating systems and instant-play web ecosystems. Its graphics system supports multiple APIs, employing physically based rendering and

This is a generative AI model library containing a collection of PyTorch and TensorFlow implementations for creating synthetic data and modeling complex probability distributions. It serves as a multi-framework repository of deep learning models designed for learning and replicating data patterns. The project provides specialized implementation suites for several generative architectures. This includes Generative Adversarial Networks using competing generator and discriminator models, Variational Autoencoder frameworks that map data to a latent space, and Restricted Boltzmann Machine and Deep

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

Hunyuan3D-2 is a machine learning framework designed to convert two-dimensional images into fully realized, textured three-dimensional meshes. It utilizes a generative artificial intelligence model to perform both shape construction and surface texture synthesis, enabling the automated creation of digital assets. The system distinguishes itself through a modular generative pipeline that separates geometry reconstruction from texture mapping. It employs multi-view image projection and latent diffusion techniques to ensure geometric consistency, while providing a plugin-based bridge architectur

Modly is a local AI 3D model generator that converts two-dimensional images into three-dimensional meshes. It is a privacy-focused tool that processes data directly on the host graphics card using GPU-accelerated inference. The system serves as an extensible AI model framework, allowing the integration of external model extensions and runtime files from remote repositories. It utilizes a manifest-driven plugin architecture to add new generation methods by loading metadata and files from external version control systems. The toolset includes a command-line interface for triggering generation

Mitsuba 3 is a high-performance physically based rendering framework that operates as a CPU and GPU render engine. It functions as a spectral rendering system and a differentiable path tracer, simulating the transport of light as spectral or polarized data through materials and geometry. The system is distinguished by its differentiable rendering pipeline, which calculates derivatives of images relative to input parameters to enable inverse rendering and optimization. It utilizes a just-in-time compilation layer to transform rendering logic into optimized kernels for hardware-agnostic executi

Mitsuba is a physically based rendering engine that calculates realistic light interactions to produce accurate synthetic images using both biased and unbiased numerical integration techniques. It is designed for computer graphics research and supports interactive three-dimensional scene inspection through a graphical interface that provides progressive real-time previewing, refining images iteratively when movement stops. The system features a plugin-based architecture that dynamically loads modular components at runtime to incorporate custom materials, light sources, and complete rendering

This project is a physically based rendering system and ray tracing engine designed to generate photorealistic images. It operates as a spectral rendering system that records radiance across discretized wavelength buckets and functions as a volumetric path tracer to compute light scattering and absorption within participating media. The engine utilizes GPU acceleration to execute its rendering pipeline on parallel graphics hardware. It integrates real-world optical data, such as measured spectral power distributions and lens description files, to simulate the behavior of physical camera syste

Filament is a real-time physically based rendering engine designed for high-fidelity 3D graphics. It functions as a cross-platform graphics library that provides a unified interface for rendering complex models and materials across desktop, mobile, and web environments. The engine distinguishes itself through a data-oriented architecture that optimizes memory usage and processing speed, alongside a shader-variant system that generates specialized code for specific material and lighting configurations. By abstracting diverse hardware graphics backends, it ensures consistent visual performance

COLMAP is a 3D scene reconstruction suite and C++ geometry library that implements a full structure-from-motion pipeline. It functions as a GPU-accelerated photogrammetry tool and multi-view stereo framework designed to produce dense 3D geometry and watertight meshes from collections of 2D images. The project distinguishes itself through hardware-accelerated feature extraction and a modular camera modeling system that supports perspective, fisheye, and equirectangular lens types. It employs vocabulary tree image retrieval to efficiently identify similar images in large datasets and provides P

OpenMoonray is a production-grade physically based rendering system and path-tracing engine. It simulates the physical behavior of light to generate high-fidelity photorealistic images and is compatible with Universal Scene Description files for visualizing complex 3D scenes and production pipelines. The system is designed as a distributed rendering framework, capable of splitting heavy computational workloads across multiple machines or cloud clusters to accelerate image generation. It integrates OpenColorIO for consistent color management across different display devices and color spaces.

MegaTTS3 is a bilingual speech synthesis system that generates natural-sounding speech in Chinese and English, including seamless code-switching within a single utterance. It functions as a text-to-speech engine, voice cloning system, and speech-to-text alignment tool, built around an acoustic latent compression model that encodes high-resolution audio into compact representations for efficient processing. The system distinguishes itself through accent intensity control, allowing adjustment of a speaker's accent strength in generated speech, and voice cloning from short audio samples for pers

Kolors is a generative model implementation for synthesizing photorealistic images from natural language descriptions and visual references. It utilizes a latent diffusion model framework to produce high-fidelity imagery, operating within a compressed latent space to improve generation efficiency and quality. The system functions as a multilingual image generator, interpreting text prompts in multiple languages to produce semantically accurate visual outputs. It includes a custom model training pipeline that uses low-rank adaptation to teach the model specific subjects or artistic styles from

LatentSync is an audio-driven video generator and latent diffusion lip sync model designed to synchronize a speaker's lip movements in a video to a target audio track. It provides a lip synchronization training framework for developing synchronization networks on custom video and audio datasets. The system utilizes a video preprocessing pipeline to clean, segment, and align face data. It includes a visual sync evaluation tool that calculates confidence scores to measure the accuracy of audio and visual alignment in generated videos. The project covers capabilities for custom synchronization