Image-to-Text
Transformers
PyTorch
Japanese
instructblip
feature-extraction
vision
image-captioning
japanese-stablelm
custom_code
Instructions to use stabilityai/japanese-instructblip-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stabilityai/japanese-instructblip-alpha 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="stabilityai/japanese-instructblip-alpha", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForVision2Seq processor = AutoProcessor.from_pretrained("stabilityai/japanese-instructblip-alpha", trust_remote_code=True) model = AutoModelForVision2Seq.from_pretrained("stabilityai/japanese-instructblip-alpha", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Ctrl+K