Update app.py

app.py

@@ -1,3 +1,38 @@
 import gradio as gr
+from transformers import pipeline
+from PIL import Image
+import requests
 
-gr.load("models/Salesforce/blip-image-captioning-large").launch()
+# Initialize the pipeline
+pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
+
+def image_caption(image, text_prompt=None):
+    # Conditional image captioning if text prompt is provided
+    if text_prompt:
+        inputs = processor(image, text_prompt, return_tensors="pt")
+        out = model.generate(**inputs)
+        caption = processor.decode(out[0], skip_special_tokens=True)
+    else:
+        # Unconditional image captioning
+        inputs = processor(image, return_tensors="pt")
+        out = model.generate(**inputs)
+        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")
+
+gr.Interface(
+    fn=image_caption,
+    inputs=[image_input, text_input],
+    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()