PartCrafter vs Tripo AI
PartCrafter
github.comTripo AI
tripo3d.aiSide by side
| Figure | PartCrafter | Tripo AI |
|---|---|---|
| Price from | Free | $4.58/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | Yes | — |
| macOS | — | Yes |
| Linux | Yes | — |
| iOS | — | Yes |
| Android | — | Yes |
| API | — | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 11 |
| Spec score · AI 3D Model Generators | 8.3 (#8) | 8.7 (#4) |
| Integrations | The README documents Gemini for part suggestions and style transfer, and says the provider architecture can be extended with other providers. | Official bridges and plugins cover Blender, 3ds Max, Unity, Unreal Engine, Maya, Godot, Cocos Creator, ZBrush, MetaTailor, Roblox and ComfyUI. |
| Support | The repository invites users to contact the maintainer by email or open an issue with questions or suggestions. | The help center has dedicated sections for billing, accounts, credits, features, privacy, enterprise and API/plugins. |
Plans
Tripo AI
- FreeFree
- Pro$20 a month
- Max$90 a month
- Team$55 a month
- FreeFree
- FreeFree
- API pay-as-you-go$0.01, paid once
- Team$55 a year
- Pro$240 a year
- Credits$1,000, paid once
In their own words
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.
Tripo AI
Tripo AI is a 3D creation platform that generates models from text, images, sketches, and multiple views. Its High Detail Model feature can create models with up to 2 million polygons for rendering, visual effects, 3D printing, e-commerce visuals, and game workflows. Smart Mesh produces quad meshes from 500 to 25,000 quads for games, animation, and VR/AR/XR. Editing tools include AI texturing, segmentation, retopology, rigging, animation, and Smart UV unwrapping. Exports include GLB, GLTF, FBX, OBJ, USDZ, STL, and 3MF. The DCC Bridge lists Blender, 3ds Max, Unity, Unreal, Maya, Cocos, Godot, and ZBrush. Developers can integrate generation through an API using API-key authentication; most generation tasks run asynchronously, with clients polling for results. Tripo is available on the web and through its API. The Free plan costs nothing and includes 200 monthly credits, one concurrent task, 15 exports, and 10 stored models. It is limited to non-commercial use, and its models are public. Tripo AI was founded in 2023 and is headquartered in Sai Ying Pun, Hong Kong.