Instructions to use nnpy/blip-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nnpy/blip-image-captioning 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="nnpy/blip-image-captioning")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("nnpy/blip-image-captioning") model = AutoModelForImageTextToText.from_pretrained("nnpy/blip-image-captioning") - Notebooks
- Google Colab
- Kaggle
Commit ·
1b67c1b
1
Parent(s): b6d2ff6
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,6 @@ output: """
|
|
| 21 |
inputs = processor(image, prompt, return_tensors="pt")
|
| 22 |
|
| 23 |
output = model.generate(**inputs, max_length=100)
|
| 24 |
-
print(tokenizer.decode(output[0]))
|
| 25 |
|
| 26 |
```
|
|
|
|
| 21 |
inputs = processor(image, prompt, return_tensors="pt")
|
| 22 |
|
| 23 |
output = model.generate(**inputs, max_length=100)
|
| 24 |
+
print(processor.tokenizer.decode(output[0]))
|
| 25 |
|
| 26 |
```
|