Update app.py

app.py

@@ -11,25 +11,26 @@ print(list_all_vqascore_models())
 # Initialize the model only once
 model_pipe = None
 
+@spaces.GPU
 def initialize_model(model_name):
-    print("Initializing model...")
     global model_pipe
     if model_pipe is None:
         model_pipe = VQAScore(model=model_name)  # our recommended scoring model
-    print("Model initialized!")
+        print("Model initialized!")
     return model_pipe
 
 @spaces.GPU
-def generate(image, text):
+def generate(model_name, image, text):
+    print("Model_name:", model_name)
     print("Image:", image)
     print("Text:", text)
-    model_pipe = initialize_model("clip-flant5-xl")
+    model_pipe = initialize_model(model_name)
     return model_pipe(images=[image], texts=[text])
 
 iface = gr.Interface(
     fn=generate,  # function to call
-    # inputs=[gr.Dropdown(["clip-flant5-xl", "clip-flant5-xxl"], label="Model Name"), gr.Image(type="pil"), gr.Textbox(label="Prompt")],  # define the types of inputs
-    inputs=[gr.Image(type="filepath"), gr.Textbox(label="Prompt")],  # define the types of inputs
+    inputs=[gr.Dropdown(["clip-flant5-xl", "clip-flant5-xxl"], label="Model Name"), gr.Image(type="filepath"), gr.Textbox(label="Prompt")],  # define the types of inputs
+    # inputs=[gr.Image(type="filepath"), gr.Textbox(label="Prompt")],  # define the types of inputs
     outputs="number",  # define the type of output
     title="VQAScore",  # title of the app
     description="This model evaluates the similarity between an image and a text prompt."