from transformers import BlipProcessor, BlipForConditionalGeneration
import torch

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

def generate_caption(image):
    inputs = processor(image, return_tensors="pt")

    with torch.no_grad():
        out = model.generate(**inputs, max_length=50, num_beams=5, early_stopping=True, no_repeat_ngram_size=2)

    caption = processor.decode(out[0], skip_special_tokens=True)
    return caption