Update app.py

app.py

@@ -1,37 +1,34 @@
-import gradio as gr
-from transformers import BlipProcessor, BlipForConditionalGeneration
-from PIL import Image
-
-# Load BLIP model and processor
-processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-vqa-base")
-
-def answer_question(image, question):
-    """
-    Generates an answer based on the given image and question.
-    """
-    try:
-        if not question.strip():
-            return "Please enter a question."
-
-        # Prepare inputs for the model
-        inputs = processor(images=image, text=question, return_tensors="pt")
-
-        # Generate answer
-        outputs = model.generate(**inputs)
-        answer = processor.decode(outputs[0], skip_special_tokens=True)
-
-        return answer
-    except Exception as e:
-        return f"An error occurred: {str(e)}"
-
-# Gradio Interface
-iface = gr.Interface(
-    fn=answer_question,  # Function to process image + question
-    inputs=[gr.Image(type="pil"), gr.Textbox(label="Ask a question about the image")],
-    outputs="text",
-    title="Visual Question Answering with BLIP",
-    description="Upload an image and ask a question about it. The model will generate an answer."
-)
-
-iface.launch()
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+
+# Load BLIP model and processor
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def caption_image(image):
+    """
+    Generates a caption for the given image.
+    """
+    try:
+        # Prepare inputs for image captioning
+        inputs = processor(images=image, return_tensors="pt")
+
+        # Generate caption
+        outputs = model.generate(**inputs)
+        caption = processor.decode(outputs[0], skip_special_tokens=True)
+
+        return caption
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=caption_image,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Image Captioning with BLIP",
+    description="Upload an image to generate a descriptive caption."
+)
+
+iface.launch()