app.py

from transformers import pipeline
import gradio as gr

# Load the image-to-text model
pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Function to generate captions
def generate_caption(image):  # Renamed 'input' to avoid conflict
    out = pipe(image)
    return out[0].get("generated_text", "No caption generated")  # Safe key access

# Create the Gradio Interface
iface = gr.Interface(fn=generate_caption, 
                     inputs=gr.Image(type="pil"),
                     outputs="text")

# Launch the app
iface.launch()