Improve model card with pipeline tag, library, and project links

Hi, I'm Niels from the Hugging Face team.

This PR improves the model card for ArcFlow by:
- Adding the `pipeline_tag: text-to-image` to the metadata for better discoverability.
- Adding `library_name: diffusers` to the metadata, as the model demonstrates clear compatibility with the Diffusers library in its usage examples and config files.
- Linking the model card to its [paper page](https://huggingface.co/papers/2602.09014) on the Hub.
- Adding a prominent link to the [official GitHub repository](https://github.com/pnotp/ArcFlow).
- Including a concise "Overview" section to briefly describe the model without adding the full abstract.

These updates aim to make the model more discoverable, provide clearer usage context, and adhere to best practices for documentation on the Hub.

README.md

@@ -1,20 +1,30 @@
 ---
-license: apache-2.0
 base_model:
 - black-forest-labs/FLUX.1-dev
 - Qwen/Qwen-Image
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: diffusers
 ---
+
 # ArcFlow
-ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
+
+[**ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation**](https://huggingface.co/papers/2602.09014)
 <br/>
-Zihan Yang<sup>1</sup>, 
-[Shuyuan Tu](https://github.com/Francis-Rings)<sup>1</sup>, 
-Licheng Zhang<sup>1</sup>, 
-[Qi Dai](https://scholar.google.com/citations?hl=en&user=NSJY12IAAAAJ)<sup>2</sup>, 
-[Yu-Gang Jiang](https://scholar.google.com/citations?hl=en&user=f3_FP8AAAAAJ)<sup>1</sup>, 
+Zihan Yang<sup>1</sup>,
+[Shuyuan Tu](https://github.com/Francis-Rings)<sup>1</sup>,
+Licheng Zhang<sup>1</sup>,
+[Qi Dai](https://scholar.google.com/citations?hl=en&user=NSJY12IAAAAJ)<sup>2</sup>,
+[Yu-Gang Jiang](https://scholar.google.com/citations?hl=en&user=f3_FP8AAAAAJ)<sup>1</sup>,
 [Zuxuan Wu](https://zxwu.azurewebsites.net/)<sup>1</sup>
 <br/>
 [<sup>1</sup>Fudan University; <sup>2</sup>Microsoft Research Asia]
+
+Official Code Repository: [pnotp/ArcFlow](https://github.com/pnotp/ArcFlow)
+
+## Overview
+ArcFlow is a few-step distillation framework that explicitly employs non-linear flow trajectories to approximate pre-trained teacher trajectories. Built on large-scale models (Qwen-Image-20B and FLUX.1-dev), ArcFlow achieves a 40x speedup with 2 NFEs over the original multi-step teachers without significant quality degradation.
+
 ## Usage
 
 Please first install the [official code repository](https://github.com/pnotp/ArcFlow).