📚 Introduction

Lumina-mGPT 2.0 is a stand-alone, decoder-only autoregressive model, trained from scratch, that unifies a broad spectrum of image generation tasks, including text-to-image generation, image pair generation, subject-driven generation, multi-turn image editing, controllable generation, and dense prediction.

🚀 Usage

We provide the implementation of Lumina-mGPT 2.0, as well as sampling code, visit our GitHub.

📽️ Demo Examples

Qualitative Performance

Comparison with Lumina-mGPT and Janus Pro

📖 Citation

If you find the provided code or models useful for your research, consider citing them as:

@misc{lumina-mgpt-2.0,
      title={Lumina-mGPT 2.0: Stand-alone Autoregressive Image Modeling},
      author={Alpha VLLM Team},
      year={2025},
      url={https://github.com/Alpha-VLLM/Lumina-mGPT-2.0},
}