Update app.py

app.py

@@ -23,6 +23,9 @@ uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png
 # Text input for prompt
 input_text = st.text_input("Enter your prompt:", "Identify the skin condition?")
 
+# Slider for max tokens
+max_new_tokens = st.slider("Maximum Output Tokens:", 10, 100, 50)
+
 # Process and display the result when the button is clicked
 if uploaded_file is not None and st.button("Analyze"):
     try:
@@ -30,21 +33,25 @@ if uploaded_file is not None and st.button("Analyze"):
         input_image = Image.open(uploaded_file).convert("RGB")
         st.image(input_image, caption="Uploaded Image", use_column_width=True)
 
+        # Resize image for efficiency
+        max_size = (512, 512)
+        input_image = input_image.resize(max_size)
+
         # Prepare inputs
-        inputs = processor(
-            text=input_text,
-            images=input_image,
-            return_tensors="pt",
-            padding="longest"
-        ).to(device)
-
-        # Generate output
-        max_new_tokens = 50
-        with torch.no_grad():
-            outputs = model.generate(**inputs, max_new_tokens=max_new_tokens)
-        
-        # Decode output
-        decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
+        with st.spinner("Processing..."):
+            inputs = processor(
+                text=input_text,
+                images=input_image,
+                return_tensors="pt",
+                padding="longest"
+            ).to(device)
+
+            # Generate output
+            with torch.no_grad():
+                outputs = model.generate(**inputs, max_new_tokens=max_new_tokens)
+            
+            # Decode output
+            decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
 
         # Display result
         st.success("Analysis Complete!")