Improve model card: Add pipeline_tag, library_name, update paper link, and clean up content

This PR enhances the model card for CoMPaSS-SD1.5, based on the paper [CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models](https://huggingface.co/papers/2412.13195).

Specifically, it addresses the following points:
- Adds `pipeline_tag: text-to-image` to the metadata, improving model discoverability via the Hugging Face Hub filters.
- Adds `library_name: diffusers` to the metadata, enabling direct integration and usage snippets within the Hub UI.
- Updates the paper link within the model card content to the official Hugging Face paper page.
- Reformats inline links for the project page, code, and paper for better readability and prominence.
- Removes a redundant title heading (`# CoMPaSS-SD1.5`) under the model description for cleaner presentation.
- Updates the BibTeX citation to include the URL to the Hugging Face paper page.
- Updates the license link to be an absolute URL for robustness.

These changes provide clearer and more structured information for users, facilitating easier discovery and understanding of the model's capabilities and usage.

README.md

@@ -1,4 +1,8 @@
 ---
+base_model: runwayml/stable-diffusion-v1-5
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: diffusers
 tags:
 - text-to-image
 - diffusers
@@ -12,31 +16,26 @@ widget:
 - text: a photo of a sheep below a sink
   output:
     url: images/sheep-below-sink.jpg
-base_model: runwayml/stable-diffusion-v1-5
-license: apache-2.0
 ---
+
 # CoMPaSS-SD1.5
 
 <Gallery />
 
 ## Model description 
 
-# CoMPaSS-SD1.5
-
-\[[Project Page]\]
-\[[code]\]
-\[[arXiv]\]
-
-A UNet that enhances spatial understanding capabilities of the StableDiffusion 1.5 text-to-image
-diffusion model.  This model demonstrates significant improvements in generating images with specific
+CoMPaSS-SD1.5 is a UNet that enhances spatial understanding capabilities of the StableDiffusion 1.5 text-to-image
+diffusion model. This model demonstrates significant improvements in generating images with specific
 spatial relationships between objects.
 
+**[Project Page](https://compass.blurgy.xyz)** | **[Code](https://github.com/blurgyy/CoMPaSS)** | **[Paper](https://huggingface.co/papers/2412.13195)**
+
 ## Model Details
 
 - **Base Model**: StableDiffusion 1.5
 - **Training Data**: SCOP dataset (curated from COCO)
 - **Framework**: Diffusers
-- **License**: Apache-2.0 (see [./LICENSE])
+- **License**: Apache-2.0 (see [./LICENSE](https://github.com/blurgyy/CoMPaSS/blob/main/LICENSE))
 
 ## Intended Use
 
@@ -55,7 +54,7 @@ spatial relationships between objects.
 
 ## Using the Model
 
-See our [GitHub repository][code] to get started.
+See our [GitHub repository](https://github.com/blurgyy/CoMPaSS) to get started.
 
 ### Effective Prompting
 
@@ -103,7 +102,8 @@ If you use this model in your research, please cite:
   title={CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models},
   author={Zhang, Gaoyang and Fu, Bingtao and Fan, Qingnan and Zhang, Qi and Liu, Runxing and Gu, Hong and Zhang, Huaqi and Liu, Xinguo},
   booktitle={ICCV},
-  year={2025}
+  year={2025},
+  url={https://huggingface.co/papers/2412.13195}
 }
 ```
 
@@ -113,9 +113,4 @@ For questions about the model, please contact <blurgy@zju.edu.cn>
 
 ## Download model
 
-Weights for this model are available in Safetensors format.
-
-[./LICENSE]: <./LICENSE>
-[Project page]: <https://compass.blurgy.xyz>
-[code]: <https://github.com/blurgyy/CoMPaSS>
-[arXiv]: <https://arxiv.org/abs/2412.13195>
+Weights for this model are available in Safetensors format.