- Home
- AI 3D Model Generators
- PartCrafter
PartCrafter
What it is
PartCrafter is an open-source 3D generative model that creates multiple 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 pre-segmented input. Its approach represents parts with disentangled latent tokens and uses hierarchical attention to carry information within and across them. Local inference scripts are installed from the GitHub repository in a Python environment. They support background removal and optional 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. Inference requires a CUDA-enabled GPU with at least 8 GB of VRAM. The project is MIT-licensed and listed as free, with no warranty. Its linked Hugging Face demo is paused; the page says users can ask the authors to restart it.
For and against
For
- Generates multiple parts from one RGB image.
- Works with objects and complex scenes.
- Does not require pre-segmented input images.
- Includes optional background removal and style transfer.
- MIT-licensed with pretrained weights available.
Against
- Inference requires a CUDA-enabled GPU with at least 8 GB VRAM.
- The linked Hugging Face demo is paused.
- The software is provided without warranty.
The verdict
PartCrafter offers image-to-3D generation with part-aware outputs and local inference scripts. Check the GPU requirement and paused demo status before choosing it.
Who it suits
PartCrafter suits people who want to generate part-level 3D objects or scenes from images and can run local inference. Users need a CUDA-enabled GPU with at least 8 GB of VRAM.
Plans and prices
PartCrafter (MIT-licensed open-source software)
MIT license · local installation requires a CUDA-enabled GPU with at least 8GB VRAM
Read 9 Oct 2026 · github.com
On the record
- Architecture
- Its method uses disentangled latent tokens for parts and a hierarchical attention mechanism for information flow within and across parts.wgsxm.github.io · read 9 Oct 2026
- Compositional architecture
- The model represents each 3D part with disentangled latent tokens and uses hierarchical attention across parts.wgsxm.github.io · read 9 Oct 2026
- Demo availability
- The linked Hugging Face demo is paused, and its page says users can ask its authors to restart it.huggingface.co · read 9 Oct 2026
- Deployment
- The official instructions install the project from its GitHub repository in a Python environment and run inference scripts locally.github.com · read 9 Oct 2026
- Hardware requirement
- The README specifies a CUDA-enabled GPU with at least 8 GB of VRAM for inference.github.com · read 9 Oct 2026
- Image preprocessing
- The inference scripts support background removal and optional style transfer to adapt real-world photos to the rendered-image domain used for training.github.com · read 9 Oct 2026
- Image styling
- An optional Gemini-powered style-transfer step converts real-world photos toward an Objaverse-style rendering before generation.github.com · read 9 Oct 2026
- Integrations
- The README documents Gemini for part suggestions and style transfer, and says the provider architecture can be extended with other providers.github.com · read 9 Oct 2026
- License
- The repository lists an MIT license.github.com · read 9 Oct 2026
- License and warranty
- The repository uses the MIT License and provides the software “AS IS,” without warranty.github.com · read 9 Oct 2026
- Model weights
- Pretrained object-level and scene-level model weights are hosted on Hugging Face.huggingface.co · read 9 Oct 2026
- Object generation
- The repository provides an inference script for generating part-level 3D objects from images.github.com · read 9 Oct 2026
- Part-aware output
- It generates semantically meaningful, geometrically distinct 3D meshes without requiring pre-segmented input images.wgsxm.github.io · read 9 Oct 2026
- Part suggestions
- An optional VLM feature can suggest the number of parts, using Gemini by default.github.com · read 9 Oct 2026
- Purpose
- PartCrafter generates multiple structured 3D parts and objects from a single RGB image in one pass.wgsxm.github.io · read 9 Oct 2026
- Scene generation
- The repository provides a separate inference script for generating 3D scenes from images.github.com · read 9 Oct 2026
- Security and compliance
- The official pages opened provide no security certification or compliance claim.github.com · read 9 Oct 2026
- Support
- The repository invites users to contact the maintainer by email or open an issue with questions or suggestions.github.com · read 9 Oct 2026
