Hunyuan 3D
AI-powered text-to-3D and image-to-3D for production-ready assets
Generate high-fidelity 3D models from text or single images with accurate geometry, clean topology, UVs, and photorealistic PBR textures. Hunyuan 3D integrates with Blender, supports real-time preview, exports GLB/OBJ/FBX, and offers Turbo variants for faster iteration.
Text-to-3D
Image-to-3D
PBR Textures
Blender Integration
What is Hunyuan 3D?
Hunyuan 3D is Tencent’s state-of-the-art unified framework for creating high-resolution 3D assets from natural language prompts or reference images. It delivers production-ready models with proper materials and UVs, supports multi-view inputs for complex objects, and includes a dedicated Hunyuan3D-Paint model for professional PBR texture synthesis.
Unified text-to-3D and image-to-3D pipelines with multi-view support for higher accuracy
High-fidelity geometry with clean topology and optimized polygon counts for real-time and production
Professional PBR texturing via Hunyuan3D-Paint, including normal maps and UV unwrapping
Blender addon for in-viewport generation, preview, and editing without leaving your workflow
Multi-format export to GLB, OBJ, and FBX compatible with Unity, Unreal Engine, Blender, and Maya
Turbo variants generate up to ~4× faster while maintaining high visual quality
API server and Python SDK for automation and large-scale content pipelines
3D asset generationOpen-source
Key Features of Hunyuan 3D
Hunyuan 3D combines cutting-edge AI technology with practical features for professional 3D asset creation.
Image-to-3D Generation
Transform single images into complete 3D models with accurate geometry, proper topology, and realistic textures—perfect for converting concept art or photos into 3D assets.
Text-to-3D Generation
Create detailed 3D models from natural language descriptions; Hunyuan 3D outputs production-ready assets with proper materials and textures.
High-Resolution Assets
Generate high-fidelity 3D models with exceptional detail, clean topology, and optimized polygon counts for real-time rendering and production.
Professional Texture Synthesis
The Hunyuan3D-Paint model creates photorealistic textures with PBR materials, normal maps, and proper UV unwrapping.
Multi-View Input Support
Improve shape accuracy and coverage by providing multiple reference views for complex objects and proportions.
Multi-Format Export
Export to GLB, OBJ, and FBX—compatible with Unity, Unreal Engine, Blender, Maya, and other major 3D tools.
Blender Integration
A dedicated Blender addon enables direct generation, preview, and editing without leaving your workflow.
API Access
Deploy in production pipelines with API server support and a Python SDK to automate large-scale 3D asset generation.
Real-time Preview
Inspect models interactively in a built-in 3D viewport—rotate, zoom, and validate before export.
Turbo Variants
Distilled models offer up to ~4× faster generation for rapid look-dev while maintaining high visual quality.
How It Works
A streamlined two-stage pipeline turns prompts or images into production-ready 3D assets.
1
1) Generate Base Geometry
Provide a text prompt or single/multi-view images, then run the Hunyuan3D geometry model to produce a clean, UV-ready mesh with optimized topology. Use Turbo variants for quick iteration and prompt refinements.
2
2) Texture, Review, and Export
Apply photorealistic PBR textures with Hunyuan3D-Paint, preview results in the Blender addon or web UI, make adjustments, and export GLB/OBJ/FBX. Integrate programmatically via the API server and Python SDK.
Hunyuan 3D Use Cases
Discover how professionals across industries leverage Hunyuan 3D for innovative 3D content creation.
Game Development
Rapidly prototype and build game-ready assets for characters, props, environments, and items to accelerate pipelines.
AR/VR Experiences
Produce immersive spatial content with original 3D assets tailored to AR/VR requirements.
Product Design
Visualize concepts in 3D for prototyping, presentations, and iteration—turn sketches into models in seconds.
Architecture Visualization
Generate furniture, fixtures, and decor elements for interior and architectural renders.
Digital Art and NFTs
Create unique 3D artwork for galleries, NFT collections, and creative projects.
E-commerce
Power online stores and configurators with interactive 3D product previews and virtual showrooms.
Film and Animation
Build 3D assets for VFX, motion graphics, and pre-production concept development.
Education and Training
Develop accurate, detailed 3D models for simulations and interactive learning materials.
Frequently Asked Questions
Everything you need to know about Hunyuan 3D—from capabilities to licensing and deployment.
What is Hunyuan 3D and what makes it unique?
It is Tencent’s state-of-the-art model for generating high-resolution 3D assets from text or images, featuring a unified text/image-to-3D framework, professional Paint texturing, large-scale architecture, multiple deployment options (including Blender), and open-source availability with comprehensive docs.
What file formats can I export?
GLB (web and real-time), OBJ (universal), and FBX (engines and DCC). Exports include materials and UVs for immediate use in Unity, Unreal, Blender, Maya, and more.
How do I access and use Hunyuan 3D?
Use Python code for maximum control, a Gradio web UI for quick tests, the Blender addon for in-DCC workflows, or deploy an API server for production. See the GitHub repository for installation and documentation.
Can I use generated assets commercially?
Hunyuan 3D is under the Tencent Hunyuan Community License. Review LICENSE and NOTICE in the repository for commercial terms, attribution, and any restrictions.
What are the system requirements?
A CUDA-capable GPU with 16 GB or more VRAM is recommended for standard models (24 GB+ ideal); mini variants can run with around 12 GB. CPU-only inference is not supported.
Standard vs. Turbo—what’s the difference?
Turbo models are distilled for approximately 4× faster generation while retaining high quality; Standard provides the highest fidelity for final assets. Both share the same inputs and exports.
How does it compare to other 3D generators?
Hunyuan 3D stands out for scale, professional PBR texturing via Paint, unified text and image pipelines, multi-view support, Turbo speed options, and open-source access.
Can I generate textured models directly?
Yes. Use a two-stage pipeline, generate geometry with Hunyuan3D-DiT, then apply PBR textures with Hunyuan3D-Paint. A Turbo option is available for faster iteration.
Ready to Create Stunning 3D Assets?
Join thousands of developers, artists, and designers using Hunyuan 3D to transform their 3D workflows. Open-source and available on GitHub with comprehensive documentation.
Related Models
Explore more AI models from the same provider
Hunyuan Motion
Hunyuan Motion is a cutting-edge text-to-3D human motion generation suite that turns natural language into high-quality, skeleton-based character animation. Built on a billion-parameter Diffusion Transformer and Flow Matching, Hunyuan Motion delivers state-of-the-art instruction following, smooth motion, and production-ready outputs with a simple prompt-to-animation workflow backed by CLI and Gradio. Learn more and get started via the official repository on [github.com](https://github.com/Tencent-Hunyuan/HY-Motion-1.0).
Learn More
Hunyuan Image
Hunyuan Image 3.0 transforms your ideas into stunning, photorealistic images with unprecedented prompt adherence and intelligent reasoning. Powered by 80B parameters and 64 experts MoE architecture, it delivers exceptional semantic accuracy and visual excellence. Experience the future of AI image generation with native multimodal understanding.
Learn More
Hunyuan Video Generator
Hunyuan Video transforms your text descriptions into stunning, high-quality videos with exceptional physical accuracy and temporal consistency. Powered by a 13B parameter Unified Diffusion Transformer architecture, it generates up to 5-second videos at 720p resolution with superior motion dynamics and visual fidelity. Experience the future of video creation with advanced Flow Matching schedulers and parallel inference capabilities.
Learn More
Hunyuan World
Transform text & images into high-quality 3D models. Unleash your creative potential.
Learn More
Hunyuan Video Avatar
Bring portraits to life. Create expressive talking-head videos from a single image and audio.
Learn More
Hunyuan Custom
Hunyuan Custom is Tencent's state-of-the-art multimodal video generation solution that allows users to create customized, subject-consistent videos using AI. Upload an image, type a prompt, or add audio/video input to generate cinematic-quality content in seconds.
Learn More