cached_exmaple=False

app.py

@@ -3,7 +3,8 @@
 
 import glob
 import gradio as gr
-import os, random
+import os
+import random
 
 import subprocess
 
@@ -70,13 +71,15 @@ def generate_image(seed, psi):
     img = iface(seed, psi)
     return img
 
+
 random.seed(1993)
 model_types = ['icon-filter', 'pifu', 'pamir']
-examples = [[item, random.choice(model_types)] for item in random.sample(sorted(glob.glob('examples/*.png')), 4)]
+examples = [[item, random.choice(model_types)] for item in random.sample(
+    sorted(glob.glob('examples/*.png')), 8)]
 
 with gr.Blocks() as demo:
     gr.Markdown(description)
-    
+
     out_lst = []
     with gr.Row():
         with gr.Column():
@@ -86,7 +89,8 @@ with gr.Blocks() as demo:
                         0, 100, step=1, default=0, label='Seed (For Image Generation)')
                     psi = gr.inputs.Slider(
                         0, 2, step=0.05, default=0.7, label='Truncation psi (For Image Generation)')
-                    radio_choice = gr.Radio(model_types, label='Method (For Reconstruction)', value='icon-filter')
+                    radio_choice = gr.Radio(
+                        model_types, label='Method (For Reconstruction)', value='icon-filter')
                 inp = gr.Image(type="filepath", label="Input Image")
             with gr.Row():
                 btn_sample = gr.Button("Sample Image")
@@ -94,29 +98,33 @@ with gr.Blocks() as demo:
 
             gr.Examples(examples=examples,
                         inputs=[inp, radio_choice],
-                        cache_examples=True,
+                        cache_examples=False,
                         fn=generate_model,
                         outputs=out_lst)
 
-            out_vid_download = gr.File(label="Download Video, welcome share on Twitter with #ICON")
+            out_vid_download = gr.File(
+                label="Download Video, welcome share on Twitter with #ICON")
 
         with gr.Column():
-            overlap_inp = gr.Image(type="filepath", label="Image Normal Overlap")
+            overlap_inp = gr.Image(
+                type="filepath", label="Image Normal Overlap")
             out_smpl = gr.Model3D(
                 clear_color=[0.0, 0.0, 0.0, 0.0],  label="SMPL")
             out_smpl_download = gr.File(label="Download SMPL mesh")
             out_smpl_npy_download = gr.File(label="Download SMPL params")
             out_recon = gr.Model3D(
-                clear_color=[0.0, 0.0, 0.0, 0.0],  label="ICON")
+                clear_color=[0.0, 0.0, 0.0, 0.0],  label="Recon")
             out_recon_download = gr.File(label="Download clothed human mesh")
             out_final = gr.Model3D(
-                clear_color=[0.0, 0.0, 0.0, 0.0],  label="ICON++")
-            out_final_download = gr.File(label="Download refined clothed human mesh")
+                clear_color=[0.0, 0.0, 0.0, 0.0],  label="Refined Recon")
+            out_final_download = gr.File(
+                label="Download refined clothed human mesh")
 
     out_lst = [out_smpl, out_smpl_download, out_smpl_npy_download, out_recon, out_recon_download,
                out_final, out_final_download, out_vid_download, overlap_inp]
 
-    btn_submit.click(fn=generate_model, inputs=[inp, radio_choice], outputs=out_lst)
+    btn_submit.click(fn=generate_model, inputs=[
+                     inp, radio_choice], outputs=out_lst)
     btn_sample.click(fn=generate_image, inputs=[seed, psi], outputs=inp)
 
 if __name__ == "__main__":