Usage:
from transformers import BlipProcessor, BlipForConditionalGeneration
import torch
from PIL import Image
processor = BlipProcessor.from_pretrained("prasanna2003/blip-image-captioning")
if processor.tokenizer.eos_token is None:
processor.tokenizer.eos_token = '<|eos|>'
model = BlipForConditionalGeneration.from_pretrained("prasanna2003/blip-image-captioning")
image = Image.open('file_name.jpg').convert('RGB')
prompt = """Instruction: Generate a single line caption of the Image.
output: """
inputs = processor(image, prompt, return_tensors="pt")
output = model.generate(**inputs, max_length=100)
print(processor.tokenizer.decode(output[0]))
- Downloads last month
- 109
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.