What is Hunyuan3D 2.0 ?
Short definition: Hunyuan3D 2.0(*Hunyuan3D-2*) is a two-stage, large-scale generative system from Tencent for producing high-resolution textured 3D assets from multimodal inputs (text, 1–4 images, sketches). The system separates shape generation (Hunyuan3D-DiT / ShapeVAE) and texture synthesis (Hunyuan3D-Paint), plus a production UI/platform (Hunyuan3D-Studio).
Main features
- Multi-modal inputs: Text-to-3D, image-to-3D (1–4 views), sketch-to-3D. The global site and docs explicitly list these modes.
- Two-stage pipeline:
- Shape generation — Hunyuan3D-DiT (latent diffusion / flow-matching on ShapeVAE latents) produces a bare mesh.
- Texture synthesis — Hunyuan3D-Paint generates multi-view images conditioned on geometry; outputs are baked into high-resolution texture maps.
- Output formats & integration: Exports common 3D formats (OBJ, GLB) and is designed to integrate with Unity, Unreal, Blender and standard production pipelines. Enterprise API supports PBR material generation and topology options (triangles/quads).
- Production features: Smart topology (mesh optimization), low-poly stylization, texture baking, and in-studio animation support (skeletal skinning via GNN for simple retargeting in Hunyuan3D-Studio).
Benchmark performance (published metrics)
From the Hunyuan3D 2.0 technical report / evaluation (representative metrics from paper Table 4; higher CLIP-score is better; lower CMMD / FID metrics are better):
| Model | CMMD (↓) | FID_CLIP (↓) | FID_Inception (↓) | CLIP-score (↑) |
|---|---|---|---|---|
| Trellis (open-source baseline) | 3.591 | 54.639 | 289.287 | 0.787 |
| Closed-source Model 1 | 3.600 | 55.866 | 305.922 | 0.779 |
| Closed-source Model 2 | 3.368 | 49.744 | 294.628 | 0.806 |
| Closed-source Model 3 | 3.218 | 51.574 | 295.691 | 0.799 |
| Hunyuan3D 2.0 (Ours) | 3.193 | 49.165 | 282.429 | 0.809 |
The authors report superior geometry detail, condition alignment fidelity and texture map quality across automatic metrics and a 300-case user study (50 participants) where Hunyuan3D 2.0 outperformed comparative methods on visual quality and adherence to the conditional image.
Representative production use cases
- Game asset generation: rapid prototyping of props, set pieces, low- and high-poly character or prop meshes + baked textures; Hunyuan3D’s low-poly stylization module + texture baking integrate into game pipelines.
- 3D e-commerce / product visualization: convert product photos or sketches into rotatable 3D product previews for catalogs.
- Creative tools / studios: sketch→3D workflows for artists, automatic UV/texture baking, and quick iteration for look development.
- AR/VR content & rapid prototyping: generate environment assets or props for immersive experiences, then optimize via the low-poly stylizer and retargeting/animation modules.
How to Use Hunyuan3D 2.0
Step 1: Sign Up for API Key
Log in to cometapi.com. If you are not our user yet, please register first. Sign into your CometAPI console. Get the access credential API key of the interface. Click “Add Token” at the API token in the personal center, get the token key: sk-xxxxx and submit.
Step 2: Send Requests to Hunyuan3D 2.0 API
Select the “"Hunyuan3D-2"” endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace <YOUR_API_KEY> with your actual CometAPI key from your account. base url is Hunyuan3D
Insert your request and image into the content field—this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results
Process the API response to get the generated answer. After processing, the API responds with the task status and output data.