AI Text & Image to 3D

Kaedim3D is an online AI platform whose main function is to quickly convert 2D images into 3D models. The tool can take concept drawings, sketches, or regular photos as input and generate 3D models that are ready for production use.Kaedim3D was originally designed to dramatically shorten the time it takes for 3D artists and game developers to...

Supercraft is a software platform that uses Artificial Intelligence (AI) to assist in the design of solid products. It changes the traditional design process that relies on complex CAD software and hand-drawn sketches. Users can quickly generate concept sketches, high-fidelity renderings and even 3D models of products by entering simple natural language commands. The...

Veltos.ai is an artificial intelligence platform that allows users to create games and 3D worlds with simple text prompts. The core idea of this tool is to make game creation easy, and users do not need to have programming or complex design skills. Whether you are a gamer, story creator or interested in developing...

Rendrix is an artificial intelligence assistant integrated into Blender designed to streamline the 3D creation process. It allows users to perform a variety of 3D tasks, manage project structure, and automate basic workflows by entering simple natural language descriptions. When a user enters a requirement, Rendrix will...

3D Bust Maker is an AI-based 3D modeling tool focused on quickly generating 3D printable bust models from a single photo. Users don't need 3D modeling experience, just upload a single photo and AI generates highly accurate 3D models in minutes, suitable for 3D printing or digital display. The platform is simple to operate...

Diffuman4D is a project developed by the ZJU3DV research team at Zhejiang University, focusing on generating high-fidelity 4D human body views from sparse view videos. The project combines spatio-temporal diffusion modeling and 4DGS (4D Gaussian Splatting) technology, which solves the difficulty of traditional methods in generating sparse input...

Fast3D is an online platform that utilizes artificial intelligence technology to quickly generate 3D models. Users can create high-quality 3D models in seconds by entering text descriptions or uploading images. The website supports multiple export formats for game development, 3D printing and animation scenarios.Fast3D operates...

Thiings is an online platform offering over 5,000 free AI-generated 3D icons for designers, developers, and other creative workers. Users can browse icons on different topics, generate custom icons, or download the entire icon library. The icons are free to use for personal and commercial projects without worrying about...

PartCrafter is an innovative open source project focused on generating editable 3D part models from a single RGB image. It uses advanced structured 3D generation technology to generate multiple semantically meaningful 3D parts simultaneously from a single image , applicable to game development, product design and other fields. The project is based on pre-training...

GenXD is an open source project developed by the National University of Singapore (NUS) and Microsoft team. It focuses on generating arbitrary 3D and 4D scenes, solving the problem of real-world 3D and 4D generation due to insufficient data and complex model design. The project analyzes camera and object motion, combined with large-scale real...

MIDI-3D is an open source project developed by the VAST-AI-Research team to quickly generate 3D scenes containing multiple objects from a single image for developers, researchers and creators. This tool is based on multi-instance diffusion modeling techniques, combining artificial intelligence and 3D modeling, and can simultaneously generate multiple...

TripoSF is an open source project built by the VAST-AI-Research team, specifically designed to quickly generate high-resolution 3D models from a single image. It uses a technique called SparseFlex, which is highly efficient and can run on common devices.TripoSF's code and pre-trained models...

TripoSG is an open source project developed by the VAST AI research team to generate high-quality 3D models from a single image. The project uses large-scale rectifier-flow converter technology, combined with hybrid supervised training and high-quality datasets, to generate 3D models with clear geometric details and complex structures.Trip...

Vibe Draw is an open source project developed by Martin Sit that allows users to turn hand-drawn sketches into beautiful 3D models. The goal of this tool is simple: to make 3D modeling easy for anyone, without the need for great artistic skills or complex software. It uses artificial intelligence techniques to take the roughest...

LHM (Large Animatable Human Reconstruction Model) is an open source project, which is developed by aigc3d team to quickly generate action-supporting 3D human models from a single image. The core feature is to use AI technology to turn 2D images into 3D models in a few seconds, supporting real...

Hunyuan3D-2 is an open source project developed by Tencent, aiming to generate high-resolution 3D models from text or images. It consists of two core components: shape generation model (Hunyuan3D-DiT) and texture generation model (Hunyuan3D-Paint). Users can enter text descriptions or upload images. ....

BlenderMCP is an open source tool that connects Blender to Claude AI via the Model Context Protocol (MCP) protocol. Users can control Blender directly with text commands to quickly create and edit 3D models, scenes and...

MagicArticulate is an AI framework developed by ByteDance in collaboration with Nanyang Technological University (NTU), focusing on rapidly transforming static 3D models into animation-enabled digital assets. It automatically generates skeletal structures and skinning weights for models through advanced autoregressive Transformer and functional diffusion modeling, greatly simplifying...

Neural4D is an innovative AI-based platform focused on helping users quickly generate high-quality 3D models and animations with simple text or image input. Developed by DreamTech, it relies on the world's leading end-to-end 3D generation of large models, where users simply provide a description or a...