minor tweaks.

app.py

@@ -108,16 +108,19 @@ with gr.Blocks() as app:
             ["Image", "Image+Video"], label="Output Format", value="Image"
         )
         im = gr.Image(label="Input Image")
+
+    with gr.Row():
+        d_t_img = gr.Image(label="Derender with Text")
+        r_d_img = gr.Image(label="Recognize and Derender")
+        vanilla_img = gr.Image(label="Vanilla")
+
     with gr.Row():
         d_t_text = gr.Textbox(
             label="OCR recognition input to the model", interactive=False
         )
         r_d_text = gr.Textbox(label="Recognition from the model", interactive=False)
         vanilla_text = gr.Textbox(label="Vanilla", interactive=False)
-    with gr.Row():
-        d_t_img = gr.Image(label="Derender with Text")
-        r_d_img = gr.Image(label="Recognize and Derender")
-        vanilla_img = gr.Image(label="Vanilla")
+
     with gr.Row():
         d_t_vid = gr.Video(label="Derender with Text", autoplay=True)
         r_d_vid = gr.Video(label="Recognize and Derender", autoplay=True)

utils.py

@@ -165,6 +165,7 @@ def plot_ink_to_video(
 
     ani = FuncAnimation(fig, update, frames=all_points + 1, blit=False)
     Writer = FFMpegWriter(fps=fps)
+    plt.tight_layout()
     ani.save(output_name, writer=Writer)
     plt.close(fig)