Update README.md

README.md

@@ -13,24 +13,40 @@ base_model: Salesforce/blip-image-captioning-base
 
 # Example Usage
 ```python
-past_the_code
-```
+import torch
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
-## Junk
+def prepare(text):
+    text = text.replace('. ','.').replace(' .','.')
+    text = text.replace('< ','<').replace(' <','<')
+    text = text.replace('> ','>').replace(' >','>')
+    text = text.replace('( ','(').replace(' (','(')
+    text = text.replace(') ',')').replace(' )',')')
+    text = text.replace(': ',':').replace(' :',':')
+    text = text.replace('_ ','_').replace(' _','_')
+    text = text.replace(',(())','')
+    for i in range(10):
+        text = text.replace(')))','))').replace('(((','((')
+    return text
 
-This model contains references to lore, they can be removed as follows:
-```python
-past_the_code
-```
+path_to_model = "blip-image2promt-stable-diffusion-v0.15"
 
-## Examples
+processor = BlipProcessor.from_pretrained(path_to_model)
+model = BlipForConditionalGeneration.from_pretrained(path_to_model, torch_dtype=torch.float16).to("cuda")
 
-```note
-paste there images table
-```
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
 
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
+
+out = model.generate(**inputs, max_new_tokens=100)
+
+out_txt = processor.decode(out[0], skip_special_tokens=True)
+
+print(prepare(out_txt))
+```
 
-| Original | Original prompt | Generated prompt by image | Generated image |
-| -------- | --------------- | ------------------------- | --------------- |
-| pass     | pass            | pass                      | pass            |