We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a unified architecture (Unified Next-DiT) that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and allowing seamless task expansion. Besides, since high-quality captioners can provide semantically well-aligned text-image training pairs, we introduce a unified captioning system, Unified Captioner (UniCap), specifically designed for T2I generation tasks. UniCap excels at generating comprehensive and accurate captions, accelerating convergence and enhancing prompt adherence. (2) Efficiency - to improve the efficiency of our proposed model, we develop multi-stage progressive training strategies and introduce inference acceleration techniques without compromising image quality. Extensive evaluations on academic benchmarks and public text-to-image arenas show that Lumina-Image 2.0 delivers strong performances even with only 2.6B parameters, highlighting its scalability and design efficiency. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-Image-2.0.
@article{arxiv.2503.21758,
title = {Lumina-Image 2.0: A Unified and Efficient Image Generative Framework},
author = {Qi Qin and Le Zhuo and Yi Xin and Ruoyi Du and Zhen Li and Bin Fu and Yiting Lu and Jiakang Yuan and Xinyue Li and Dongyang Liu and Xiangyang Zhu and Manyuan Zhang and Will Beddow and Erwann Millon and Victor Perez and Wenhai Wang and Conghui He and Bo Zhang and Xiaohong Liu and Hongsheng Li and Yu Qiao and Chang Xu and Peng Gao},
journal= {arXiv preprint arXiv:2503.21758},
year = {2025}
}