Add pipeline tag, library name, and abstract to model card

This PR improves the model card for T2I-R1 by:
- Adding the `pipeline_tag: text-to-image` to the metadata, which significantly enhances the model's discoverability on the Hugging Face Hub for users filtering by this specific pipeline.
- Adding `library_name: transformers` to the metadata. The presence of `config.json` and a `transformers_version` suggests compatibility with the Hugging Face Transformers library, allowing users to more easily integrate the model.
- Including the paper's abstract in the content section. This provides immediate, comprehensive context about the model's objectives, approach, and key findings directly on the model page, making it more informative for visitors.
- The existing arXiv paper link has been retained as per instructions.

README.md

@@ -1,13 +1,17 @@
 ---
-license: apache-2.0
 base_model:
 - deepseek-ai/Janus-Pro-7B
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: transformers
 ---
+
 # 🌟🔥 T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
 
 Official checkpoint for the paper "[T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://arxiv.org/pdf/2505.00703)".
 
-Paper: https://arxiv.org/pdf/2505.00703
+## Abstract
+Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: this https URL
 
 Code: https://github.com/CaraJ7/T2I-R1
 
@@ -18,5 +22,5 @@ Please refer to the instructions in GitHub to set up the repository first then r
 cd t2i-r1/src/infer
 python reason_inference.py \
 --model_path YOUR_MODEL_CKPT \
---data_path test_data.txt 
+--data_path test_data.txt
 ```