Hugging Face's logo

Kwai-Kolors
/
CoTyle

Text-to-Image
Diffusers
Safetensors
QwenImagePipeline
art
Model card Files
xet
 Community
1

Improve model card: update pipeline tag, add library, and detailed content

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+171
-3
nielsr

This PR significantly enhances the model card for Kwai-Kolors/CoTyle.

Key improvements include:

  • Updated Metadata:
    • Corrected the pipeline_tag from image-text-to-text to text-to-image, accurately reflecting the model's functionality (generating images from text prompts and a style code).
    • Added library_name: diffusers, as the model is built upon and compatible with the Diffusers library, enabling better integration and discoverability on the Hub.
  • Comprehensive Content:
    • Incorporated a detailed introduction, news, ToDo list, and the abstract directly from the paper's GitHub README.
    • Included prominent links and badges to the paper, project page, Hugging Face demo, Hugging Face model, and the GitHub repository.
    • Provided detailed "Quick Start" instructions, including environment setup, download steps, and command-line usage examples for both single and batch image generation, directly from the GitHub README.
    • Added information about the Gradio app for local interactive inference.
    • Included the full academic citation and acknowledgements.

This update makes the model card much more informative and user-friendly for anyone exploring the CoTyle model.
Improve model card: update pipeline tag, add library, and detailed content1a071af5
liuhuijie6410 changed pull request status to merged

Sign up or log in to comment