Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915407462400000 |
|---|---|
| author | Xin, Yi Yan, Juncheng Qin, Qi Li, Zhen Liu, Dongyang Li, Shicheng Huang, Victor Shea-Jay Zhou, Yupeng Zhang, Renrui Zhuo, Le Han, Tiancheng Sun, Xiaoqing Luo, Siqi Wang, Mengmeng Fu, Bin Cao, Yuewen Li, Hongsheng Zhai, Guangtao Liu, Xiaohong Qiao, Yu Gao, Peng |
| author_facet | Xin, Yi Yan, Juncheng Qin, Qi Li, Zhen Liu, Dongyang Li, Shicheng Huang, Victor Shea-Jay Zhou, Yupeng Zhang, Renrui Zhuo, Le Han, Tiancheng Sun, Xiaoqing Luo, Siqi Wang, Mengmeng Fu, Bin Cao, Yuewen Li, Hongsheng Zhai, Guangtao Liu, Xiaohong Qiao, Yu Gao, Peng |
| contents | We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenization scheme allows the model to seamlessly handle a wide spectrum of tasks-including subject-driven generation, image editing, controllable synthesis, and dense prediction-within a single generative framework. To further boost usability, we incorporate efficient decoding strategies like inference-time scaling and speculative Jacobi sampling to improve quality and speed, respectively. Extensive evaluations on standard text-to-image benchmarks (e.g., GenEval, DPG) demonstrate that Lumina-mGPT 2.0 not only matches but in some cases surpasses diffusion-based models. Moreover, we confirm its multi-task capabilities on the Graph200K benchmark, with the native Lumina-mGPT 2.0 performing exceptionally well. These results position Lumina-mGPT 2.0 as a strong, flexible foundation model for unified multimodal generation. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-mGPT-2.0. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling Xin, Yi Yan, Juncheng Qin, Qi Li, Zhen Liu, Dongyang Li, Shicheng Huang, Victor Shea-Jay Zhou, Yupeng Zhang, Renrui Zhuo, Le Han, Tiancheng Sun, Xiaoqing Luo, Siqi Wang, Mengmeng Fu, Bin Cao, Yuewen Li, Hongsheng Zhai, Guangtao Liu, Xiaohong Qiao, Yu Gao, Peng Computer Vision and Pattern Recognition We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenization scheme allows the model to seamlessly handle a wide spectrum of tasks-including subject-driven generation, image editing, controllable synthesis, and dense prediction-within a single generative framework. To further boost usability, we incorporate efficient decoding strategies like inference-time scaling and speculative Jacobi sampling to improve quality and speed, respectively. Extensive evaluations on standard text-to-image benchmarks (e.g., GenEval, DPG) demonstrate that Lumina-mGPT 2.0 not only matches but in some cases surpasses diffusion-based models. Moreover, we confirm its multi-task capabilities on the Graph200K benchmark, with the native Lumina-mGPT 2.0 performing exceptionally well. These results position Lumina-mGPT 2.0 as a strong, flexible foundation model for unified multimodal generation. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-mGPT-2.0. |
| title | Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.17801 |