Image-to-Text
Transformers
Safetensors
English
blip
image-text-to-text
image-captioning
vision-language
flickr8k
coco
Instructions to use Amirhossein75/Image-Captioning-Blip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Amirhossein75/Image-Captioning-Blip 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="Amirhossein75/Image-Captioning-Blip")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Amirhossein75/Image-Captioning-Blip") model = AutoModelForImageTextToText.from_pretrained("Amirhossein75/Image-Captioning-Blip") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 379a78f2ea5ef7ebed05424a9adb599b0f77c1a67f225d850d0f68b5b8005f3f
- Size of remote file:
- 990 MB
- SHA256:
- 79fd8dc78ed12025f574730b4b1b6ec0d28c87beed3955483fc703b578c877c7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.