Create app.py

app.py

@@ -0,0 +1,23 @@
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to("cuda")
+
+img_url = 'https://www.chitramala.in/wp-content/gallery/pawan-kalyan-pspk25-movie-working-stills/PSPK-25-Movie-Location-Photos-5.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+# >>> a photography of a woman and her dog
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt").to("cuda")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))