Improve model card: Add pipeline tag, sample usage, and BibTeX

README.md

@@ -1,7 +1,8 @@
-
 ---
 license: mit
+pipeline_tag: image-to-video
 ---
+
 # Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
 
 <table>
@@ -20,4 +21,32 @@ license: mit
 </table>
 
 [Arian Mousakhan](https://lmb.informatik.uni-freiburg.de/people/mousakha/), [Sudhanshu Mittal](https://lmb.informatik.uni-freiburg.de/people/mittal/) , [Silvio Galesso](https://lmb.informatik.uni-freiburg.de/people/galessos/), [Karim Farid](https://lmb.informatik.uni-freiburg.de/people/faridk/), [Thomas Brox](https://lmb.informatik.uni-freiburg.de/people/brox/index.html)
-<br>University of Freiburg<br>
+<br>University of Freiburg<br>
+
+## Sample Usage
+
+To perform autoregressive video generation (roll-out) using example input frames, follow these steps:
+
+First, clone the repository and set up the environment:
+```bash
+git clone https://github.com/lmb-freiburg/orbis.git
+cd orbis
+conda env create -f environment.yml
+conda activate orbis_env
+```
+
+Then, run the `rollout.py` script:
+```bash
+python evaluate/rollout.py --exp_dir logs_wm/orbis_288x512 --num_gen_frames 120 --num_steps 30
+```
+This command will generate 120 frames over 30 steps using the model located in `logs_wm/orbis_288x512`.
+
+## BibTeX
+```bibtex
+@article{mousakhan2025orbis,
+  title={Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models},
+  author={Mousakhan, Arian and Mittal, Sudhanshu and Galesso, Silvio and Farid, Karim and Brox, Thomas},
+  journal={arXiv preprint arXiv:2507.13162},
+  year={2025}
+}
+```