Instructions to use Salesforce/blip-image-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-base") - Notebooks
- Google Colab
- Kaggle
BlipProcess import
#4
by matheusdias - opened
ImportError: cannot import name 'BlipProcessor' from 'transformers' (/usr/local/lib/python3.8/dist-packages/transformers/init.py)
Hi @matheusdias blip has not been released yet in transformers via pypi, therefore you need to install transformers from source to use blip:
pip uninstall transformers
pip install git+https://github.com/huggingface/transformers.git@main
Thank you for letting me know!
Thanks! Closing as considering this as resolved, let us know if the problem still persists
ybelkada changed discussion status to closed