Update README.md

README.md

@@ -3,4 +3,18 @@ license: apache-2.0
 base_model:
 - alibaba-pai/CogVideoX-Fun-V1.5-5b-InP
 ---
-This is the model card for VOID: Video Object Interaction Deletion. Pass_1 and Pass_2 models correspond to the initial and optional refinement pass for object and associated interaction removal.
+
+# VOID: Video Object and Interaction Deletion
+<div style="line-height: 1;">
+  <a href="https://void-model.github.io/" target="_blank" style="margin: 2px;">
+    <img alt="Website" src="https://img.shields.io/badge/Website-VOID-4285F4" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://arxiv.org/abs/XXXX.XXXXX" target="_blank" style="margin: 2px;">
+    <img alt="arXiv" src="https://img.shields.io/badge/arXiv-VOID-FBBC06" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+
+</div>
+
+This is the model card for VOID: Video Object Interaction Deletion. 
+It is built on top of [CogVideoX](https://github.com/THUDM/CogVideo) and fine-tuned for video inpainting with interaction-aware mask conditioning.
+Pass_1 and Pass_2 models correspond to the initial and optional refinement pass for object and associated interaction removal.