from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import gradio as gr

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")

def image_to_prompt(image):
    inputs = processor(images=image, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=50)
    caption = processor.decode(outputs[0], skip_special_tokens=True)
    return caption

iface = gr.Interface(
    fn=image_to_prompt,
    inputs=gr.Image(type="pil"),
    outputs=gr.Textbox(label="Generated Prompt"),
    title="Image to Prompt Generator (using BLIP)",
    description="Upload an image and get a text prompt describing it.",
)

iface.launch()