Update app.py

app.py

@@ -12,8 +12,6 @@ print(list_all_vqascore_models())
 model_pipe = None
 
 def initialize_model(model_name):
-    import torch
-    torch.jit.script = lambda f: f
     print("Initializing model...")
     global model_pipe
     if model_pipe is None:
@@ -21,14 +19,16 @@ def initialize_model(model_name):
     print("Model initialized!")
     return model_pipe
 
+model_pipe = initialize_model("clip-flant5-xl")
+
 @spaces.GPU
-def generate(model_name, image, text):
-    pipe = initialize_model(model_name)
-    return pipe(image, text)
+def generate(image, text):
+    return model_pipe(image, 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.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="pil"), 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."