nielsr HF Staff commited on
Commit
3b5d0ff
·
verified ·
1 Parent(s): ef99e61

Improve model card with metadata and citation

Browse files

This PR enhances the model card by:

- Adding the `library_name` and `license` to the metadata section for improved searchability and clarity. The `library_name` is set to `diffusers`, reflecting the model's implementation. The license is assumed to be MIT, pending verification. Please update if incorrect.
- Including the full citation for the paper in the model card for proper attribution.

The Gradio demo and GitHub links were already present and are retained.

Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -1,6 +1,9 @@
1
  ---
2
  pipeline_tag: text-to-image
 
 
3
  ---
 
4
  ![Lumina-Image 2.0](./Demo.png)
5
  Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transformer capable of generating images from text descriptions. For more information, visit our [GitHub](https://github.com/Alpha-VLLM/Lumina-Image-2.0).
6
 
@@ -30,4 +33,22 @@ image = pipe(
30
  generator=torch.Generator("cpu").manual_seed(0)
31
  ).images[0]
32
  image.save("lumina_demo.png")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  ```
 
1
  ---
2
  pipeline_tag: text-to-image
3
+ library_name: diffusers
4
+ license: mit
5
  ---
6
+
7
  ![Lumina-Image 2.0](./Demo.png)
8
  Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transformer capable of generating images from text descriptions. For more information, visit our [GitHub](https://github.com/Alpha-VLLM/Lumina-Image-2.0).
9
 
 
33
  generator=torch.Generator("cpu").manual_seed(0)
34
  ).images[0]
35
  image.save("lumina_demo.png")
36
+ ```
37
+
38
+ This is a Hugging Face Diffusers implementation of the paper [Lumina-Image 2.0: A Unified and Efficient Image Generative Framework](https://arxiv.org/abs/2503.21758).
39
+
40
+ ## Citation
41
+
42
+ If you find the provided code or models useful for your research, consider citing them as:
43
+
44
+ ```bib
45
+ @misc{lumina2,
46
+ author={Qi Qin and Le Zhuo and Yi Xin and Ruoyi Du and Zhen Li and Bin Fu and Yiting Lu and Xinyue Li and Dongyang Liu and Xiangyang Zhu and Will Beddow and Erwann Millon and Victor Perez,Wenhai Wang and Yu Qiao and Bo Zhang and Xiaohong Liu and Hongsheng Li and Chang Xu and Peng Gao},
47
+ title={Lumina-Image 2.0: A Unified and Efficient Image Generative Framework},
48
+ year={2025},
49
+ eprint={2503.21758},
50
+ archivePrefix={arXiv},
51
+ primaryClass={cs.CV},
52
+ url={https://arxiv.org/pdf/2503.21758},
53
+ }
54
  ```