Enhance model card: Add `transformers` library, `text-to-image` pipeline tag, paper, GitHub, and project links

This PR enhances the `BAGEL-RecA` model card by:

- Adding `library_name: transformers` to the metadata. This enables the automated "How to use" widget on the Hugging Face Hub, providing users with direct code snippets for model inference.
- Updating the `pipeline_tag` from `any-to-any` to `text-to-image`. This aligns the model with its primary and highlighted capability in text-to-image generation as evidenced by the paper's benchmarks, improving discoverability for users searching for models in this domain.
- Adding explicit links to the paper ([Reconstruction Alignment Improves Unified Multimodal Models](https://huggingface.co/papers/2509.07295)), the project page ([https://reconstruction-alignment.github.io/](https://reconstruction-alignment.github.io/)), and the code repository ([https://github.com/HorizonWind2004/reconstruction-alignment](https://github.com/HorizonWind2004/reconstruction-alignment)) at the top of the model card. This provides clearer and more direct access to key resources for researchers and developers.

These changes collectively improve the model's visibility, usability, and adherence to Hugging Face Hub best practices.

README.md

@@ -1,18 +1,29 @@
 ---
-license: apache-2.0
+base_model:
+- ByteDance-Seed/BAGEL-7B-MoT
 datasets:
 - jackyhate/text-to-image-2M
 language:
 - en
 - zh
-base_model:
-- ByteDance-Seed/BAGEL-7B-MoT
-pipeline_tag: any-to-any
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: transformers
 ---
+
 # BAGEL-RecA
 
 > A self-supervised training framework that aligns understanding and generation in modest compute, with huge **zero-shot** gain on generation and editing capability.
 
+## Paper
+[Reconstruction Alignment Improves Unified Multimodal Models](https://huggingface.co/papers/2509.07295)
+
+## Project Page
+https://reconstruction-alignment.github.io/
+
+## Code
+https://github.com/HorizonWind2004/reconstruction-alignment
+
 This repository hosts the model weights for **BAGEL-RecA**. We fine-tuned BAGEL on 6 80GB NVIDIA A800 for only 27 GPU hours. While the understanding capability remains unchanged, our ReAlign method brings +3.6 **zero-shot improvement** on GenEval , +1.26 on DPGBench, +0.37 on ImgEdit and +0.33 on GEdit.
 
 For installation, usage instructions, and further documentation, please visit BAGEL's original [GitHub repository](https://github.com/bytedance-seed/BAGEL).
@@ -65,4 +76,14 @@ If you find our work inspiring or use our codebase in your research, please cons
       archivePrefix={arXiv},
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2509.07295}, 
-}
+}
+
+---
+
+<div align="center">
+  
+  ⭐ **If you find this project helpful, please consider giving it a star!** ⭐
+  
+  [![Star History Chart](https://api.star-history.com/svg?repos=HorizonWind2004/reconstruction-alignment&type=Date)](https://www.star-history.com/#HorizonWind2004/reconstruction-alignment&Date)
+
+</div>