Update README.md
Browse files
README.md
CHANGED
@@ -21,4 +21,42 @@ base_model:
|
|
21 |
- Qwen/Qwen2.5-3B-Instruct
|
22 |
tags:
|
23 |
- anything-to-image
|
24 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
- Qwen/Qwen2.5-3B-Instruct
|
22 |
tags:
|
23 |
- anything-to-image
|
24 |
+
---
|
25 |
+
|
26 |
+
|
27 |
+
|
28 |
+
|
29 |
+
<div align="center">
|
30 |
+
<h1>X2I</h1>
|
31 |
+
<a href="https://export.arxiv.org/abs/2503.06134">📜 X2I Paper </a>
|
32 |
+
|
33 |
+
<a href="https://github.com/OPPO-Mente-Lab/X2I">🌐 Github </a>
|
34 |
+
</div>
|
35 |
+
|
36 |
+
|
37 |
+
> **X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation**
|
38 |
+
|
39 |
+
<div align="center">
|
40 |
+
<img src="versatile.png">
|
41 |
+
</div>
|
42 |
+
|
43 |
+
|
44 |
+
## Citation
|
45 |
+
|
46 |
+
🌟 If you find our work helpful, please consider citing our paper and leaving valuable stars
|
47 |
+
|
48 |
+
```
|
49 |
+
@misc{ma2025x2i,
|
50 |
+
title={X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation},
|
51 |
+
author={Jian Ma and Qirong Peng and Xu Guo and Chen Chen and Haonan Lu and Zhenyu Yang},
|
52 |
+
year={2025},
|
53 |
+
eprint={2503.06134},
|
54 |
+
archivePrefix={arXiv},
|
55 |
+
primaryClass={cs.CV}
|
56 |
+
}
|
57 |
+
```
|
58 |
+
|
59 |
+
## License
|
60 |
+
|
61 |
+
This model is released under the [Apache 2.0 License](LICENSE).
|
62 |
+
|