Hunyuan3D vs PartCrafter
Hunyuan3D
3d.hunyuan.tencent.comPartCrafter
github.comSide by side
| Figure | Hunyuan3D | PartCrafter |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | Yes | Yes |
| macOS | Yes | — |
| Linux | Yes | Yes |
| API | Yes | — |
| Self-hosted | Yes | Yes |
| Plans published | 6 | 1 |
| Spec score · AI 3D Model Generators | 9.1 (#1) | 8.3 (#8) |
| Hardware requirement | The repository states that shape generation needs 10 GB VRAM, texture generation 21 GB, and combined shape and texture generation 29 GB. | The README specifies a CUDA-enabled GPU with at least 8 GB of VRAM for inference. |
| Integrations | Tencent says generated assets can be integrated into Unity, Unreal Engine, and Blender workflows. | The README documents Gemini for part suggestions and style transfer, and says the provider architecture can be extended with other providers. |
| Support | The Hunyuan3D-2.1 repository points users to WeChat and Discord groups to discuss the project and get help. | The repository invites users to contact the maintainer by email or open an issue with questions or suggestions. |
Plans
Hunyuan3D
- Tencent Hunyuan 3D new-user credit packFree
- Hunyuan 3D 1,000-credit pack100 CNY, paid once
- Hunyuan 3D 10,000-credit pack980 CNY, paid once
- Hunyuan 3D 50,000-credit pack4,750 CNY, paid once
- Hunyuan 3D 100,000-credit pack9,000 CNY, paid once
- Hunyuan 3D pay-as-you-goPriced on request
In their own words
Hunyuan3D
Hunyuan3D is Tencent’s system for generating 3D assets from text, images, or sketches. The international platform accepts up to four multi-view images, offers model editing and adjustment, and exports OBJ and GLB files. Its capabilities include text-to-3D, image-to-shape, and texture generation; Smart Topology supports triangular and quadrilateral faces. Tencent Cloud documents API tasks for generation, texturing, topology reduction, component generation, UV mapping, motion, auto-rigging, and format conversion. Hunyuan3D-2.1 releases full model weights and training code, and its repository documents a local Gradio app. A Blender add-on is listed for Hunyuan3D-2. The stated VRAM needs are 10 GB for shape generation, 21 GB for texture generation, and 29 GB for both. First-time API activation grants 100 credits, valid for one year. Paid packs include 1,000 credits for 100 CNY, paid once and 10,000 for 980 CNY, paid once; pay-as-you-go is billed at 0.12 yuan per credit, with monthly settlement.
PartCrafter
PartCrafter is a free, open-source model that generates multiple 3D parts and objects from a single RGB image. It can handle individual objects and complex scenes, producing distinct meshes with meaningful part structure without requiring a pre-segmented image. Its architecture represents parts with disentangled latent tokens and uses hierarchical attention to pass information within and across parts. Local inference scripts can remove backgrounds and optionally apply style transfer to adapt real-world photos toward the rendered-image domain used for training. An optional vision-language feature can suggest the number of parts; Gemini is the default provider, and the provider architecture can be extended. Pretrained object-level and scene-level weights are hosted on Hugging Face. Installation is from the GitHub repository in a Python environment, and inference requires a CUDA-enabled GPU with at least 8 GB of VRAM. The linked Hugging Face demo is paused, though its page says users can ask the authors to restart it. The repository lists an MIT license and provides the software as-is, without warranty.