Skip to content

erenovic/llm-blender-modeling

Repository files navigation

vllm-blender

An LLM project using VLLM and BlenderNet to generate 3D Assets for Three.JS development. This project is built upon the foundational work of BlenderLLM by FreedomIntelligence.

CI Coverage Python 3.11+ License: MIT

Installation

pip install vllm_blender

Quick Start

Python API

from vllm_blender.main import hello_world

# Basic usage
result = hello_world()
print(result)  # "Hello from vllm-blender!"

# With a name
result = hello_world("Alice")
print(result)  # "Hello, Alice, from vllm-blender!"

Command Line

python -m vllm_blender

Development

Setup

  1. Clone the repository:
git clone https://github.com/erenovic/vllm_blender.git
cd vllm_blender
  1. Set up development environment:
make all  # Install dependencies, pre-commit hooks, and run all checks

Development Commands

make help          # Show all available commands
make install-dev   # Install development dependencies
make fmt           # Format code with ruff
make lint          # Lint code with ruff
make typecheck     # Type check with mypy
make test          # Run tests
make test-cov      # Run tests with coverage
make ci            # Run all CI checks locally
make clean         # Clean build artifacts

Features

  • ✅ Modern Python packaging with pyproject.toml
  • ✅ Code formatting and linting with Ruff
  • ✅ Static type checking with mypy
  • ✅ Testing with pytest and coverage reporting
  • ✅ Pre-commit hooks for code quality
  • ✅ GitHub Actions CI/CD

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Acknowledgments

This project builds upon the work of BlenderLLM by FreedomIntelligence.

Citation

If you use this project or find it helpful, please consider citing the original BlenderLLM work:

@misc{du2024blenderllmtraininglargelanguage,
      title={BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement},
      author={Yuhao Du and Shunian Chen and Wenbo Zan and Peizhao Li and Mingxuan Wang and Dingjie Song and Bo Li and Yan Hu and Benyou Wang},
      year={2024},
      eprint={2412.14203},
      archivePrefix={arXiv},
      primaryClass={cs.HC},
      url={https://arxiv.org/abs/2412.14203},
}

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

A toy example for generating (very) low-poly objects using LLMs. LLM model is based on BlenderNet.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published