from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import torch

model_id = "muhammedaydiiinnn/blip-flickr8k-caption"

processor = BlipProcessor.from_pretrained(model_id)
model = BlipForConditionalGeneration.from_pretrained(model_id)

image = Image.open("test.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")

with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=30)

caption = processor.decode(output[0], skip_special_tokens=True)
print(caption)