Improve model card with abstract, library tag, and code link

This PR enhances the model card for Show-o2 by:

- Adding the detailed paper abstract to provide a better understanding of the model.
- Including `library_name: transformers` metadata, as the model leverages components from the 🤗 Transformers library (e.g., Qwen2.5).
- Integrating a direct link to the specific GitHub repository for Show-o2, making it easier for users to access the code.

README.md

@@ -1,11 +1,12 @@
 ---
 license: apache-2.0
 pipeline_tag: any-to-any
+library_name: transformers
 ---
+
 <div align="center">
 <br>
 
-
 [//]: # (<h3>Show-o2: Improved Unified Multimodal Models</h3>)
 
 [Jinheng Xie](https://sierkinhane.github.io/)<sup>1</sup>&nbsp;
@@ -14,9 +15,13 @@ pipeline_tag: any-to-any
 
 <sup>1</sup> [Show Lab](https://sites.google.com/view/showlab/home?authuser=0), National University of Singapore&nbsp; <sup>2</sup> Bytedance&nbsp;
  
-[![ArXiv](https://img.shields.io/badge/Arxiv-<2506.15564>-<COLOR>.svg)](https://arxiv.org/abs/2506.15564) [![WeChat badge](https://img.shields.io/badge/微信-加入-green?logo=wechat&amp)](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg)
+[![ArXiv](https://img.shields.io/badge/Arxiv-<2506.15564>-<COLOR>.svg)](https://arxiv.org/abs/2506.15564) [![Code](https://img.shields.io/badge/Code-<GitHub_Repository>-<COLOR>.svg)](https://github.com/showlab/Show-o/tree/main/show-o2) [![WeChat badge](https://img.shields.io/badge/微信-加入-green?logo=wechat&amp)](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg)
 </div>
 
+## Abstract
+
+This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at this https URL .
+
 ## What is the new about Show-o2?
 We perform the unified learning of multimodal understanding and generation on the text token and **3D Causal VAE space**, which is scalable for **text, image, and video modalities**. A dual-path of spatial (-temporal) fusion is proposed to accommodate the distinct feature dependency  of multimodal understanding and generation. We employ specific heads with **autoregressive modeling and flow matching** for the overall unified learning of **multimodal understanding, image/video and mixed-modality generation.**
 <img src="overview.png" width="1000">
@@ -76,4 +81,4 @@ To cite the paper and model, please use the below:
 }
 ```
 ### Acknowledgments
-This work is heavily based on [Show-o](https://github.com/showlab/show-o).
+This work is heavily based on [Show-o](https://github.com/showlab/Show-o).