Hugging Face's logo

KangLiao
/
Puffin

Text-to-3D
unified multimodal model
camera-centric
generation
understanding
spatial intelligence
3D vision
Model card Files
xet
Community
1

Improve model card: add pipeline tag, license, abstract, and sample usage

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+61
-6
nielsr

This PR enhances the model card for Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation by:

  • Adding the pipeline_tag: text-to-3d to the metadata, improving discoverability on the Hugging Face Hub.
  • Adding the license: other to the metadata, with the specific "NTU S-Lab License 1.0" detailed in the content.
  • Updating the paper link to the official Hugging Face Papers page: https://huggingface.co/papers/2510.08673.
  • Including the paper's abstract for a more comprehensive overview.
  • Adding a "Sample Usage" section with a code snippet for camera-controllable image generation, directly sourced from the project's GitHub repository.
  • Adding the main banner image from the GitHub repository for better visual context.
  • Consolidating and clarifying the project links.
Improve model card: add pipeline tag, license, abstract, and sample usage4b394de0
KangLiao changed pull request status to merged

Sign up or log in to comment