Awesome GitHub RepositoriesDiffusion-Based 3D Generators

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

Neural Doodle is a collection of neural network tools designed for image upscaling, texture synthesis, and semantic-guided style transfer between visual inputs. It provides a semantic style transfer engine and an example-based image upscaler that increase image resolution by referencing visual details from a target style example. The project includes a neural texture synthesizer for creating seamless bitmap textures and repeating patterns from a single input style image. It also functions as an image generation tool capable of transforming simple sketches and photos into detailed artwork. Th

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

Dream Textures is a Stable Diffusion integration for Blender that provides tools for text-to-image generation, depth projection, and node-based processing within a 3D environment. It functions as an AI texture generator capable of producing image textures and concept art from text prompts and scene renders. The system features a depth-to-image projection tool that maps generated imagery onto 3D models using depth data for spatial alignment. It also includes a node-based AI image processor for creating procedural visual effects and a dedicated toolset for AI-assisted inpainting and outpainting

AlphaFold3 is a biomolecular structure prediction model and bioinformatics structural analysis tool. It uses a deep learning system to predict the three-dimensional shapes of proteins, DNA, RNA, and ligands. The system functions as a diffusion-based protein folding model that predicts the spatial coordinates of biomolecular atoms and interactions. It utilizes a GPU-accelerated inference pipeline to process genetic sequences and structural templates for molecular modeling. The project covers structural bioinformatics analysis and protein interaction modeling to determine the physical arrangem

Point-e is a system for 3D model synthesis that generates three-dimensional point clouds from natural language descriptions and two-dimensional images. It utilizes diffusion models to synthesize these spatial representations based on text prompts or source images. The project includes specialized tools for refining these outputs, such as a point cloud upsampler to increase the density and resolution of low-resolution models. It also provides a mesh converter that uses distance function regression to transform raw point cloud data into structured 3D meshes. The broader capability surface cove

Wonder3D ist ein diffusionsbasiertes System für die 3D-Rekonstruktion aus einem einzelnen Bild. Es generiert hochdetaillierte 3D-Meshes aus einem einzelnen Eingabebild, indem es konsistente Multi-View-Normal-Maps und Farbbilder erzeugt. Die Pipeline fungiert als Multi-View-Normal-Map-Generator und Extraktor für texturierte Meshes. Sie nutzt domänenübergreifende Multi-View-Synthese zur Erstellung sichtabhängiger Maps, die anschließend durch Radiance-Fusion und speichereffiziente Oberflächenrekonstruktion in 3D-Geometrie umgewandelt werden. Das Projekt deckt 3D-Mesh-Generierung, Multi-View-Generierung und texturierte 3D-Modellierung ab. Es enthält zudem Funktionen zum Training von Diffusionsmodellen, um die Konsistenz der generierten sichtabhängigen Maps zu optimieren.

GET3D ist ein generatives 3D-Mesh-Modell und Rendering-Framework, das darauf ausgelegt ist, hochwertige texturierte Formen und tetraedrische Meshes zu synthetisieren. Es fungiert als Image-to-3D-Rekonstruktor und Text-to-3D-Generator und nutzt einen differenzierbaren 3D-Renderer, um realistische visuelle Perspektiven und Materialeffekte zu erzeugen. Das System ermöglicht die Erstellung von 3D-Assets aus einzelnen 2D-Bildern, Punktwolken oder beschreibenden Text-Prompts. Es verfügt über einen Latent-Space-Interpolator für fließende Übergänge zwischen verschiedenen 3D-Objekten und unterstützt die unabhängige Steuerung von Geometrie und Textur. Das Projekt deckt eine breite Palette von 3D-Generierungsfunktionen ab, einschließlich Voxel-to-Shape-Synthese, Novel-View-Synthese und unüberwachter Materialschätzung. Es bietet zudem Tools für die Isosurface-Extraktion und die Generierung physik-bereiter tetraedrischer Meshes.

Boltz is a deep learning molecular modeler and biomolecular structure prediction system. It uses neural network architectures to simulate the physical folding and docking of biomolecules, specifically predicting the three-dimensional shapes of protein and ligand complexes. The project functions as a protein-ligand complex predictor and binding affinity predictor, estimating the strength and probability of molecular interactions between ligands and targets. These capabilities are applied to computer aided drug design, including ligand binding affinity prediction and protein-ligand interaction

This repository is a collection of node-based pipeline configurations, examples, and templates for generating AI media. It provides a workflow library and a curated gallery of blueprints designed for creating images, videos, and 3D assets using diffusion models. The project specifically offers a set of pre-configured node graphs for implementing advanced image generation and refinement techniques, with a focus on Stable Diffusion workflows. These examples demonstrate how to interconnect processing nodes to define complex generative logic without writing code. The available templates cover a

Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D geometries. It functions as an asset generator that produces high-quality 3D meshes and textures using a flow-matching system. The project includes a specialized synthesizer for creating photorealistic textures with physically based rendering properties. These tools allow for the simulation of metallic reflections and light interactions on generated models. The system covers 3D asset pipeline automation through a sequence of shape generation and mesh refinement. It also provi