Hugging Face's logo

lglg666
/
SongGeneration-base-new

Model card Files
xet
Community
1

Improve model card for LeVo: High-Quality Song Generation with `text-to-audio` pipeline tag and detailed usage

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+400
-3
nielsr

This PR significantly enhances the model card for LeVo: High-Quality Song Generation with Multi-Preference Alignment by:

  • Adding the pipeline_tag: text-to-audio to improve discoverability on the Hugging Face Hub.
  • Providing a comprehensive description of the model, including its abstract and key features from the paper and GitHub README.
  • Including direct links to the official paper, project page, GitHub repository, and Hugging Face Space demo.
  • Adding detailed installation instructions and usage examples with code snippets extracted directly from the GitHub README, focusing on the generate.sh script and input formats.
  • Including information about the Gradio UI and evaluation performance tables.

This update ensures that users can easily understand the model's capabilities and quickly get started with its usage.

 Improve model card for LeVo: High-Quality Song Generation with `text-to-audio` pipeline tag and detailed usagead326f90
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment