import requests from PIL import Image

from transformers import BlipForConditionalGeneration, AutoProcessor

img_url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSQuFg4LTHUattLGPU0kLzYpBGHRtuqgJY8Gho3uZe_cg&s' image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

model = BlipForConditionalGeneration.from_pretrained("Fatehmujtaba/BLIP-Image-to-recipe").to(device) processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")

inputs = processor(images=image, return_tensors="pt").to(device) pixel_values = inputs.pixel_values generated_ids = model.generate(pixel_values=pixel_values, max_length=50) generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]