# tencent-hunyuan/hunyuan3d-2.1

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/tencent-hunyuan-hunyuan3d-2-1).**

2,910 stars · 409 forks · Python · other

## Links

- GitHub: https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1
- Homepage: https://3d.hunyuan.tencent.com/
- awesome-repositories: https://awesome-repositories.com/repository/tencent-hunyuan-hunyuan3d-2-1.md

## Topics

`3d` `3d-aigc` `3d-generation` `hunyuan3d` `image-to-3d` `shape` `shape-generation` `text-to-3d` `texture-genertaion`

## Description

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 provides utilities for fine-tuning pre-trained weights and training code to customize the generation process for specific applications.

## Tags

### Graphics & Multimedia

- [Image-to-Mesh Generation](https://awesome-repositories.com/f/graphics-multimedia/image-to-mesh-generation.md) — Provides a complete pipeline for converting single 2D images into three-dimensional polygonal mesh representations. ([source](https://cdn.jsdelivr.net/gh/tencent-hunyuan/hunyuan3d-2.1@main/README.md))
- [Generative PBR Textures](https://awesome-repositories.com/f/graphics-multimedia/pbr-material-authoring/generative-pbr-textures.md) — Synthesizes photorealistic material maps including metallic, roughness, and albedo properties for realistic light simulation.
- [Single-Image 3D Reconstructions](https://awesome-repositories.com/f/graphics-multimedia/single-image-3d-reconstructions.md) — Implements a flow-matching system to reconstruct a complete 3D digital model from a single photograph.
- [3D Asset Pipelines](https://awesome-repositories.com/f/graphics-multimedia/3d-asset-pipelines.md) — Automates the end-to-end conversion of flat images into fully textured 3D models for digital environments.
- [Iterative Geometry Refinement](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/3d-math-and-geometry-toolkits/mesh-modeling-tools/mesh-optimization/iterative-geometry-refinement.md) — Transforms initial coarse shapes into high-fidelity geometries through a sequence of iterative optimization and smoothing passes.

### Artificial Intelligence & ML

- [Flow-Matching Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-diffusion-models/flow-matching-frameworks.md) — Utilizes a flow-matching pipeline to transform Gaussian noise into initial 3D asset shapes.
- [Texture Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/diffusion-based-3d-generators/texture-synthesis.md) — Produces photorealistic PBR maps by iteratively denoising image latent spaces conditioned on mesh geometry.
- [3D Asset Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/3d-asset-generators.md) — Functions as a generative framework that synthesizes 3D meshes and textures from image inputs.
- [Image-Conditioned 3D Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/conditional-image-generation/image-conditioned-3d-generation.md) — Implements a system where 2D image features guide the flow-matching process to synthesize matching 3D geometries.
- [Latent Space Generative Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models.md) — Compresses complex 3D geometric data into lower-dimensional vectors to accelerate generation and sampling.