Instructions to use Salesforce/blip-image-captioning-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-large 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-large")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large") model = AutoModelForMultimodalLM.from_pretrained("Salesforce/blip-image-captioning-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
18903c0
1
Parent(s): 0b7cde4
Update README.md (#4)
Browse files- Update README.md (18221a40e4da5b2ff3f880de931b7ac631e39935)
Co-authored-by: Daniele Acquaviva <dacquaviva@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -72,7 +72,7 @@ from PIL import Image
|
|
| 72 |
from transformers import BlipProcessor, BlipForConditionalGeneration
|
| 73 |
|
| 74 |
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
|
| 75 |
-
model = BlipForConditionalGeneration.from_pretrained("
|
| 76 |
|
| 77 |
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
|
| 78 |
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|
|
|
|
| 72 |
from transformers import BlipProcessor, BlipForConditionalGeneration
|
| 73 |
|
| 74 |
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
|
| 75 |
+
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to("cuda")
|
| 76 |
|
| 77 |
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
|
| 78 |
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|