CPU3DAI tools for 3D, video and audio

Hunyuan3D 2.1: 3D Generator — What It Does and What You Need to Run It

Hunyuan3D 2.1 is a 3D generator from Tencent that solves the image-to-3D task. The tool converts a flat image into a 3D object with PBR materials suitable for production use. The code is open source, and the model weights are publicly available.

What it does

The authors describe Hunyuan3D 2.1 as a system that creates highly detailed 3D objects with ready-made PBR materials. It is built around the image-to-3D task, but the repository tags also mention text-to-3D — the developers provide no details about that mode. The output consists of shape and texture. Generation can be run either separately or together.

What you need to run it

The code is written in Python. The developer states that testing was done on Python 3.10 and PyTorch 2.5.1+cu124. The hunyuan3d-2 library is required. The authors describe the VRAM requirements as follows: shape generation takes 10 GB of VRAM, texture generation takes 21 GB, and the full shape-plus-texture cycle takes 29 GB. The largest weights file is 6.9 GB, and the total size of all files is 13.9 GB. The code and weights are distributed under the Tencent Hunyuan 3D 2.1 Community License: commercial use is permitted with a monthly audience of up to 1 million users, but the license does not apply in the EU, the UK, or South Korea. Running on your own hardware is possible, but the full Hunyuan3D 2.1 generation cycle requires a GPU with 29 GB of memory. No cloud service is listed in the fact sheet, though a project website exists — the authors do not disclose details about its functionality.

Who it suits

Hunyuan3D 2.1 is aimed at those who need to generate 3D models from images with materials ready for further work. The tool will be useful to artists, game developers, and visualization specialists who have access to a powerful GPU. It is not suitable for those expecting fast results on consumer GPUs: the memory requirements are high. Also keep in mind that commercial use is limited to an audience of up to 1 million users per month. Hunyuan3D 2.1 continues Tencent's line of tools for generating 3D content. The open source code and available weights make it possible to study how the model works, but practical use runs up against the hardware requirements and the commercial-use limit of an audience of up to 1 million users per month.
Hunyuan3D 2.1 pipeline 3D model generation from images Image Input data Raster format Single image Shape generation Shape Generation VRAM: 10 GB Model geometry Texture generation Texture Generation VRAM: 21 GB PBR materials 3D model Final asset Shape + texture Total VRAM: 29 GB Two operating modes Shape only (10 GB) or shape + texture (29 GB) Python 3.10 + PyTorch 2.5.1 | Open source | License: verification required Model: tencent/Hunyuan3D-2.1 | Weights: 13.9 GB | Max file: 6.9 GB
How the Hunyuan3D 2.1 pipeline works. The diagram is drawn from the tool’s fact sheet.

Fact sheet

Taskimage-to-3d source
Code licenseTencent Hunyuan 3D 2.1 Community License: commercial use up to 1M MAU source
Weights licenseTencent Hunyuan 3D 2.1 Community License: commercial use up to 1M MAU source
VRAM10–29 GB per the author’s description source
Largest weights file6.9 GB source
All weights files13.9 GB source
Python3.10 per the author’s description source
Libraryhunyuan3d-2 source
LanguagePython source
Last code change2025-10-17 source
Repository created2025-06-13 source
Changes often — as of 2026-09-14
GitHub stars3957 source
Forks596 source
Downloads per month57267 source
Model updated2025-10-17 source

Values are collected automatically from official sources and were checked on 2026-09-14. Each one links to its source, and values taken from the developer’s pages also carry a verbatim quote — hover over the note. Pricing and versions are shown as of the check date and change most often; verify on the vendor’s site before buying.

See also