Improve model card: Add pipeline tag, library, paper, code & usage
#1
by
nielsr
HF Staff
- opened
This PR significantly improves the model card for the ARRA-Adapt-MIMIC-7B model by:
- Adding the
pipeline_tag: text-to-image, making the model discoverable in the text-to-image category on the Hub. - Adding
library_name: transformers, which enables the automatic "How to use" widget on the model page. - Explicitly linking to the paper: Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment.
- Providing a direct link to the GitHub repository: https://github.com/xiexing0916/ARRA.
- Including a "Sample Usage" code snippet, directly sourced from the GitHub README, to guide users on how to generate images with the model, specifically tailored for X-ray generation.
- Incorporating the paper's abstract and key visual results from the GitHub repository to provide more comprehensive information.
Please review these additions and merge if they align with the guidelines.
xing0916
changed pull request status to
merged
Thanks for your nice work! I have merged them.