Update app.py

app.py

@@ -35,7 +35,6 @@ def generate_advanced_description(image, detail_level, emotion_focus, style_focu
         return "Please upload an image to generate a description."
     
     # Process image for both models
-    blip2_inputs = blip2_processor(images=image, return_tensors="pt").to(device)
     blip_inputs = blip_processor(images=image, return_tensors="pt").to(device)
     
     # Basic prompts for different aspects
@@ -54,10 +53,13 @@ def generate_advanced_description(image, detail_level, emotion_focus, style_focu
             basic_caption = blip_processor.decode(basic_outputs[0], skip_special_tokens=True)
             
             # Get detailed description from BLIP-2
+            # BLIP-2 requires text input to be processed with the image
+            text = "a detailed description: " + combined_prompt
+            blip2_inputs = blip2_processor(image, text=text, return_tensors="pt").to(device)
+            
             outputs = blip2_model.generate(
                 **blip2_inputs,
                 max_length=150 + (detail_level * 50),
-                prompt=combined_prompt,
                 num_beams=5,
                 min_length=50,
                 top_p=0.9,