Improve CoMPaSS-FLUX.1 Model Card: Add pipeline_tag, library_name, and format links

This PR enhances the model card for CoMPaSS-FLUX.1 by:

- **Adding `pipeline_tag: text-to-image` and `library_name: diffusers`** to the metadata. This ensures the model is correctly categorized on the Hugging Face Hub and enables the automated "Use in Diffusers" widget, as the model explicitly states "Framework: Diffusers" in its description.
- **Improving the visibility of key links** (Project Page, Code, arXiv paper) by moving them to prominent inline links at the top of the model card.
- **Integrating the paper title** "CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models" into the main heading and the model description for better context.
- **Removing a redundant heading** and updating the "Using the Model" link for overall clarity and consistency.

These changes will make the model more discoverable and easier to use for the community.

README.md

@@ -1,4 +1,10 @@
 ---
+base_model: black-forest-labs/FLUX.1-dev
+license: other
+license_name: compass-lora-weights-nc-license
+license_link: LICENSE
+pipeline_tag: text-to-image
+library_name: diffusers
 tags:
 - text-to-image
 - lora
@@ -14,26 +20,18 @@ widget:
 - text: a photo of a horse to the left of a bottle
   output:
     url: images/horse-left-bottle.jpg
-base_model: black-forest-labs/FLUX.1-dev
-instance_prompt: null
-license: other
-license_name: compass-lora-weights-nc-license
-license_link: LICENSE
 ---
-# CoMPaSS-FLUX.1
 
-\[[Project Page]\]
-\[[code]\]
-\[[arXiv]\]
+# CoMPaSS-FLUX.1: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
 
-<Gallery />
+[Project Page](https://compass.blurgy.xyz) | [Code](https://github.com/blurgyy/CoMPaSS) | [arXiv](https://arxiv.org/abs/2412.13195)
 
-## Model description 
+<Gallery />
 
-# CoMPaSS-FLUX.1
+## Model description
 
 A LoRA adapter that enhances spatial understanding capabilities of the FLUX.1 text-to-image
-diffusion model. This model demonstrates significant improvements in generating images with specific
+diffusion model. This model, presented in [CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models](https://arxiv.org/abs/2412.13195), demonstrates significant improvements in generating images with specific
 spatial relationships between objects.
 
 ## Model Details
@@ -62,7 +60,7 @@ 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
 
@@ -124,7 +122,4 @@ Weights for this model are available in Safetensors format.
 
 [Download](/blurgy/CoMPaSS-FLUX.1/tree/main) them in the Files & versions tab.
 
-[./LICENSE]: <./LICENSE>
-[Project page]: <https://compass.blurgy.xyz>
-[code]: <https://github.com/blurgyy/CoMPaSS>
-[arXiv]: <https://arxiv.org/abs/2412.13195>
+[./LICENSE]: <./LICENSE>