Choose Language

Transform Images to Editable 3D Models

PartPacker uses NVIDIA's breakthrough AI technology to convert single 2D images into interconnected, editable 3D models. Generate part-based 3D models perfect for content creation, 3D printing, and advanced research applications.

Loading PartPacker Demo...

Trusted by Researchers & Creators

PartPacker represents a breakthrough in 3D generation technology, enabling novel workflows that were previously impossible with traditional single-mesh models.

518×518
Input Resolution
High-quality image processing
16GB+
VRAM Support
Professional-grade requirements
2024
Latest AI Tech
Cutting-edge Diffusion Transformer
NVIDIA
Research Labs
Backed by industry leaders

Why Choose PartPacker?

Dual-volume packing strategy for part-based generation with individual part manipulation for editing and animations

Single Image Input

PartPacker requires only a single 2D RGB image to generate comprehensive 3D models, unlike competitors that need multiple viewpoints.

Part-Based Generation

Revolutionary dual-volume packing strategy creates interconnected parts that can be individually manipulated.

Diffusion Transformer

Advanced DiT architecture ensures high-quality 3D model output with superior detail and accuracy.

Editable Components

Generated models feature separable parts perfect for animations, modifications, and interactive applications.

3D Printing Ready

Export to STL/3MF formats optimized for multi-material 3D printing applications.

Research Development

Enables novel 3D generation methods for academic research and professional development.

How PartPacker Works

Transform any 2D image into editable 3D components in three simple steps

01

Upload Image

Simply upload any 2D RGB image (518×518 resolution recommended) to begin the PartPacker generation process. Our system accepts JPEG, PNG, and other common image formats.

02

AI Processing

Our Diffusion Transformer architecture analyzes your image and generates interconnected 3D parts using dual-volume packing strategy. The AI identifies object components and creates separable parts.

03

Download & Edit

Receive your editable 3D model with separable components, ready for animation, modification, or 3D printing. Export in multiple formats including STL, GLTF, and 3MF.

Use Cases & Applications

Discover how PartPacker transforms workflows across industries

Content Creation

Generate editable 3D assets for games, films, and interactive media from concept art or reference images.

  • Game asset generation
  • Film prop creation
  • Interactive media assets
  • Virtual reality content

3D Printing

Create printable models with separable components for multi-material 3D printing and rapid prototyping.

  • Rapid prototyping
  • Multi-material printing
  • Custom part creation
  • Product design iteration

Education & Research

Advance 3D generation research and teach complex 3D modeling concepts with intuitive tools.

  • Academic research
  • Algorithm development
  • Educational demonstrations
  • Student projects

Product Design

Transform product sketches into editable 3D models for design validation and manufacturing preparation.

  • Concept visualization
  • Design validation
  • Manufacturing prep
  • Client presentations

Frequently Asked Questions

Everything you need to know about PartPacker

What image formats does PartPacker support?

PartPacker supports common image formats including JPEG, PNG, and BMP. For optimal results, we recommend using high-quality images with a resolution of 518×518 pixels. The system automatically resizes images to the optimal processing resolution.

What are the hardware requirements?

PartPacker requires a GPU with at least 16GB of VRAM for optimal performance. The system supports NVIDIA GPUs with CUDA capability. For local installation, you'll need Python 3.8+, PyTorch, and CUDA-compatible drivers.

Can I use PartPacker for commercial projects?

PartPacker is currently available for non-commercial use under NVIDIA's research license. For commercial applications, please contact NVIDIA Research for licensing information and commercial usage terms.

What output formats are supported?

PartPacker generates 3D models in multiple formats including STL for 3D printing, GLTF for web applications, OBJ for general 3D software compatibility, and 3MF for advanced multi-material 3D printing. Each part can be exported separately or as a complete assembly.

How long does the generation process take?

Generation time varies depending on image complexity and hardware specifications. Typically, the process takes 2-5 minutes on recommended hardware. The web demo may have longer processing times due to shared resources.

Can I edit the generated 3D models?

Yes! PartPacker's key innovation is generating part-based 3D models where individual components can be separated, moved, rotated, and edited independently. This makes the models perfect for animations, modifications, and interactive applications.

Resources & Documentation

Access code, models, and comprehensive documentation

GitHub Repository

Access the complete PartPacker source code, installation guides, and example scripts. Contribute to the project and stay updated with the latest developments.

View Repository

Hugging Face Hub

Download pre-trained models, explore the interactive demo, and access model documentation. Perfect for getting started quickly.

Visit Hub

Research Paper

Read the original research paper detailing the dual-volume packing strategy and technical implementation of PartPacker.

Read Paper

Documentation

Comprehensive guides covering installation, usage, API reference, and best practices for getting the most out of PartPacker.

View Docs

Video Tutorials

Step-by-step video tutorials covering everything from basic usage to advanced techniques and integration workflows.

Watch Videos

Community

Join the PartPacker community to share results, get help, and collaborate with other researchers and creators.

Join Community