How to use Wang9738/blip-image-captioning-base-Opticalvehicle-finetuned with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Wang9738/blip-image-captioning-base-Opticalvehicle-finetuned") model = AutoModelForImageTextToText.from_pretrained("Wang9738/blip-image-captioning-base-Opticalvehicle-finetuned")
SFconvertbot