prithivMLmods/Beetz-Image-Captioning-Blip

Running the model on GPU

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

processor = BlipProcessor.from_pretrained("prithivMLmods/Beetz-Image-Captioning-Blip")
model = BlipForConditionalGeneration.from_pretrained("prithivMLmods/Beetz-Image-Captioning-Blip").to("cuda")

img_url = '' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))