Hugging Face's logo

double8fun
/
ODTSR

Image-to-Image
Model card Files
xet
Community
2

Improve model card: Add pipeline tag, library name, paper, code, and detailed content

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+115
-3
nielsr

This PR significantly improves the model card for ODTSR: One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution.

Key additions include:

  • Metadata: pipeline_tag: image-to-image for better discoverability and library_name: diffusers for compatibility with the Hugging Face diffusers library.
  • Comprehensive Content:
    • An introductory overview of the model and its capabilities, synthesized from the paper abstract and GitHub README.
    • Key features of the model, extracted directly from the GitHub README.
    • Visual results with descriptive text and images, sourced from the GitHub repository.
    • Detailed installation instructions.
    • Inference instructions, including script-based and Gradio demo usage.
    • Links to the official Hugging Face paper page (https://huggingface.co/papers/2511.17138) and the GitHub repository (https://github.com/RedMediaTech/ODTSR).
    • A BibTeX citation for the paper.
    • License and acknowledgment information.

This update aims to provide a more informative and user-friendly model card for the community.

Please review and merge if everything looks good.

 Improve model card: Add pipeline tag, library name, paper, code, and detailed contentb47c8f34
double8fun changed pull request status to merged
double8fun
 Owner

Thanks for PR!

Sign up or log in to comment