blurgy

/

CoMPaSS-SD1.5

like 6

This PR enhances the model card for CoMPaSS-SD1.5, based on the paper CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models.

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.