Update app.py

app.py

@@ -2,10 +2,15 @@ import gradio as gr
 from transformers import pipeline
 from PIL import Image
 import requests
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
 # Initialize the pipeline
 pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
 
+# Initialize processor and model
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
 def image_caption(image, text_prompt=None):
     # Conditional image captioning if text prompt is provided
     if text_prompt:
@@ -19,15 +24,10 @@ def image_caption(image, text_prompt=None):
         caption = processor.decode(out[0], skip_special_tokens=True)
     return caption
 
-# Initialize processor and model
-from transformers import BlipProcessor, BlipForConditionalGeneration
-processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
-
 # Define the Gradio interface
-image_input = gr.inputs.Image(type="pil", label="Upload an Image")
-text_input = gr.inputs.Textbox(lines=1, placeholder="Optional: Enter text prompt", label="Text Prompt")
-output = gr.outputs.Textbox(label="Generated Caption")
+image_input = gr.Image(type="pil", label="Upload an Image")
+text_input = gr.Textbox(lines=1, placeholder="Optional: Enter text prompt", label="Text Prompt")
+output = gr.Textbox(label="Generated Caption")
 
 gr.Interface(
     fn=image_caption,
@@ -35,4 +35,4 @@ gr.Interface(
     outputs=output,
     title="Image Captioning with BLIP",
     description="Upload an image and get a generated caption. Optionally, provide a text prompt for conditional captioning."
-).launch()
+).launch()