Image-to-Image

Improve model card: Add pipeline tag, paper, and comprehensive details

#1
by nielsr HF Staff - opened

This PR significantly enhances the model card for DarkIR by:

  • Adding the pipeline_tag: image-to-image to the metadata for better discoverability on the Hub.
  • Linking the model directly to its paper, DarkIR: Robust Low-Light Image Restoration.
  • Including the official GitHub repository link: https://github.com/cidautai/DarkIR.
  • Incorporating a link to the Hugging Face Space demo for easy access.
  • Providing a comprehensive description of the model based on the paper's abstract and the GitHub README, including:
    • Key features and motivation.
    • Teaser images, network architecture, and gallery examples (with updated raw GitHub image links).
    • Detailed installation instructions with a code snippet.
    • Dataset information and quantitative results.
    • Sample usage for inference on images and videos, with code snippets.
    • The BibTeX citation for proper attribution.
    • Contact information.

This update makes the model card much more informative and user-friendly.

danifei changed pull request status to merged

Sign up or log in to comment