Enhance model card with metadata, links, and usage

by nielsr HF Staff - opened Nov 21, 2025

←

nielsr

Nov 21, 2025

This PR significantly enhances the model card by:

Adding pipeline_tag: text-to-image for better discoverability on the Hugging Face Hub.
Specifying library_name: diffusers as the model's configuration (_diffusers_version, SD3ControlNetModel) indicates compatibility with the Diffusers library, enabling the automated 'how to use' widget.
Linking to the official paper: SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation.
Including links to the project page (https://henghuiding.com/SceneDesigner/) and the GitHub repository (https://github.com/FudanCVL/SceneDesigner).
Incorporating the full abstract and the "Quick Start" instructions for installation and running the Gradio demo from the original GitHub README.

Please review and merge this PR if everything looks good.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

· Sign up or log in to comment