Update app.py

app.py

@@ -123,6 +123,22 @@ def video_vision(video_input_path, prompt):
 with gr.Blocks() as demo:
     with gr.Column():
         gr.Markdown("# Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos")
+        gr.HTML("""
+        <div style="display:flex;column-gap:4px;">
+            <a href="https://github.com/magic-research/Sa2VA">
+                <img src='https://img.shields.io/badge/GitHub-Repo-blue'>
+            </a> 
+            <a href="https://arxiv.org/abs/2501.04001">
+                <img src='https://img.shields.io/badge/ArXiv-Paper-red'>
+            </a>
+            <a href="https://huggingface.co/spaces/fffiloni/Sa2VA-simple-demo?duplicate=true">
+                <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-sm.svg" alt="Duplicate this Space">
+            </a>
+            <a href="https://huggingface.co/fffiloni">
+                <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-me-on-HF-sm-dark.svg" alt="Follow me on HF">
+            </a>
+        </div>
+        """)
         with gr.Tab("Single Image"):
             with gr.Row():
                 with gr.Column():
@@ -148,7 +164,7 @@ with gr.Blocks() as demo:
                         submit_video_btn = gr.Button("Submit", scale=1)
                 with gr.Column():
                     vid_output_res = gr.Textbox(label="Response")
-                    output_video = gr.Video(label="Segmentation")
+                    output_video = gr.Gallery(label="Segmentation")
             
             submit_video_btn.click(
                 fn = video_vision,