#3838th of 42 in Image and videoFor image, video and design, 3d
hunyuan3d-2
Image-to-3D mesh and texture generation models from Tencent
- Stars
- 15.3k
- License
- custom license
- Last commit
- Oct 2025
- Language
- Python
13,344 on 10 Apr 202615,274 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
No commits in the last year.
Overview
Hunyuan3D 2.0 generates textured 3D assets in two stages: a flow-based diffusion transformer (Hunyuan3D-DiT) produces a mesh from an image, then Hunyuan3D-Paint creates a texture map. It ships a diffusers-style Python API, a Gradio app, an HTTP API server and a Blender addon, with multiview, mini and turbo variants of the shape model. Shape generation needs about 6 GB VRAM, and shape plus texture about 16 GB.
Who it is for: Developers and 3D artists generating textured meshes from images locally
Strengths
- Two-stage pipeline lets Paint texture handcrafted meshes as well as generated ones
- Variants cover multiview input, 0.6B mini, and turbo/fast distilled models
- Several interfaces: Python API, Gradio app, HTTP API server, Blender addon
- Shape-only generation runs in about 6 GB VRAM
Weaknesses
- Texture generation needs custom_rasterizer and differentiable_renderer built from source
- Full shape plus texture generation needs about 16 GB VRAM
- License is reported as NOASSERTION; terms must be checked in the repo
- No Docker image or tagged release; TensorRT version still unchecked in the plan
What it needs
- GPU required
- Needs PyTorch, Gradio, trimesh, Hugging Face model weights
- Models: Hunyuan3D-DiT, Hunyuan3D-Paint, Hunyuan3D-2mini, Hunyuan3D-2mv, Hunyuan3D-Delight
- port 8080
Quick answers
Is hunyuan3d-2 open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Does hunyuan3d-2 need a GPU?
Yes, it needs a GPU.
Also in Image and video
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 91 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 87 out of 100 |
| 3 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 86 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 83 out of 100 |
| #5 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 83 out of 100 |