Add pipeline tag, library name, paper, and code links

This PR enhances the model card by:
- Adding `pipeline_tag: image-to-image` to improve discoverability for relevant tasks on the Hub.
- Specifying `library_name: diffusers` due to evidence of compatibility (`_diffusers_version` in `config.json`), which will enable an automated usage snippet.
- Including a direct link to the paper: [OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation](https://huggingface.co/papers/2512.08294).
- Adding an explicit link to the GitHub repository for the code: [https://github.com/LAW1223/OpenSubject](https://github.com/LAW1223/OpenSubject).

These changes improve the model's documentation and user experience on the Hugging Face Hub.

README.md

@@ -1,8 +1,12 @@
 ---
 license: apache-2.0
+library_name: diffusers
+pipeline_tag: image-to-image
 ---
+
 # OmniGen2-OpenSubject
 
 This repository provides an **open-source baseline** model, obtained by fine-tuning **OmniGen2** on the sampled 500k **OpenSubject** corpus and 100k internal T2I samples to maintain prompt-following ability. The model is optimized for **subject-driven image generation**, while maintaining general **prompt-following** ability.
 
-For usage examples of **OpenSubject**, please refer to: https://github.com/LAW1223/OpenSubject.
+- **Paper**: [OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation](https://huggingface.co/papers/2512.08294)
+- **Code**: [https://github.com/LAW1223/OpenSubject](https://github.com/LAW1223/OpenSubject)