Hugging Face's logo

KevinHuang
/
OmniX

Text-to-3D
Diffusers
panorama
generation
perception
flow-matching
text-to-image
image-to-image
Model card Files
xet
 Community
3

Improve model card: Update pipeline tag, add library_name, extend tags, and import full GitHub README content

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+130
-3
nielsr

This PR significantly improves the model card for OmniX by:

  • Updating the pipeline_tag to text-to-3d to accurately reflect its core capability of generating graphics-ready 3D scenes.
  • Adding library_name: diffusers as the model's codebase is built on the Diffusers library, as evidenced by the acknowledgements in the GitHub README.
  • Extending tags with text-to-image and image-to-image to cover the model's panorama generation and perception capabilities from text and image prompts.
  • Incorporating a comprehensive overview, installation instructions, detailed inference examples with code snippets, and visual demonstrations directly from the project's GitHub README to provide a rich and informative model card.
  • Ensuring direct links to the paper (arXiv), project page, and GitHub repository are prominently displayed using badges.
Improve model card: Update pipeline tag, add library_name, extend tags, and import full GitHub README content223f49eb
KevinHuang changed pull request status to merged

Sign up or log in to comment