sanaka87

/

BAGEL-RecA

like 26

This PR enhances the BAGEL-RecA model card by:

• Adding library_name: transformers to the metadata. This enables the automated "How to use" widget on the Hugging Face Hub, providing users with direct code snippets for model inference.
• Updating the pipeline_tag from any-to-any to text-to-image. This aligns the model with its primary and highlighted capability in text-to-image generation as evidenced by the paper's benchmarks, improving discoverability for users searching for models in this domain.
• Adding explicit links to the paper (Reconstruction Alignment Improves Unified Multimodal Models), the project page (https://reconstruction-alignment.github.io/), and the code repository (https://github.com/HorizonWind2004/reconstruction-alignment) at the top of the model card. This provides clearer and more direct access to key resources for researchers and developers.

These changes collectively improve the model's visibility, usability, and adherence to Hugging Face Hub best practices.