Hunyuan3D
by Tencent · github.com ↗
Open Tencent Hunyuan diffusion models for high-resolution textured 3D asset generation from images or text.
3d-generation open-weights diffusion
- Category
- 3D & Spatial
- Business model
- Open (open weights/source)
- Availability
- Global
- Launched
- 2025-01
- Record updated
- 2026-09-10
- License
- See repository LICENSE
- Founded
- 1998
- Headquarters
- CN
- Canonical URL
- https://globalaiproductindex.com/products/hunyuan3d/
Overview
Hunyuan3D is Tencent Hunyuan's family of large-scale diffusion models for generating high-resolution textured 3D assets. Hunyuan3D 2.0 weights and code are published on GitHub (Tencent-Hunyuan/Hunyuan3D-2), with a technical report on arXiv. It is an open research and self-host offering, distinct from the Hunyuan chat assistant indexed separately.
Key features
- Large-scale diffusion models for textured 3D assets
- Open weights and code on GitHub
- High-resolution mesh and texture generation
- Technical report describing the 2.0 generation
Use cases
- Self-hosted image- or text-to-3D research and products
- Generating high-resolution textured meshes
- Evaluating open 3D diffusion models
Pricing
Hunyuan3D 2.0 code and weights are published on GitHub; running them requires your own GPUs. License terms are in the repository LICENSE file.
Frequently asked questions
What is Hunyuan3D?
Hunyuan3D is Tencent's open diffusion model family for high-resolution textured 3D asset generation.
Is Hunyuan3D the same as Hunyuan chat?
No. Hunyuan chat is indexed as an AI assistant. Hunyuan3D is a 3D generation model family.
Where are the weights?
Hunyuan3D-2 is published at github.com/Tencent-Hunyuan/Hunyuan3D-2, with a paper on arXiv.
Similar products
- 3D AI Studio — Web platform that generates 3D models from text or images using multiple AI engines, with mesh cleanup and exports.
- Kaedim — AI 3D production service that turns sketches and photos into 3D assets for studios and brands.
- Meshy — AI tool that generates 3D models and textures from text prompts and images.
- Rodin — 3D generative model from Deemos that creates production-ready 3D assets from text and images.
- Skybox AI — AI service from Blockade Labs that generates 360-degree panoramic skybox scenes from text prompts.
- Sloyd — Web AI 3D generator that creates models from text, images, or parametric bases, with plugins for production tools.
Sources
This record was last reviewed on 2026-09-10.
Machine-readable record: /api/products/hunyuan3d.json · Spot an error? Suggest a correction