Update app.py

app.py

@@ -1,29 +1,19 @@
-from transformers import pipeline
-image_captioner = pipeline("image-to-text",model="Salesforce/blip-image-captioning-large")
-#Set up Prerequisites for Image Captioning App User Interface
-import os
-import io
-import IPython.display
 from PIL import Image
-import base64
-
+import requests
 import gradio as gr
 
-def image_to_base64_str(pil_image):
-    byte_arr = io.BytesIO()
-    pil_image.save(byte_arr, format='PNG')
-    byte_arr = byte_arr.getvalue()
-    return str(base64.b64encode(byte_arr).decode('utf-8'))
-def captioner(image):
-    base64_image = image_to_base64_str(image)
-    result = image_captioner(base64_image)
-    return result[0]['generated_text']
-gr.close_all()
-ImageCaptionApp = gr.Interface(fn=captioner,
-                    inputs=[gr.Image(label="Upload image", type="pil")],
-                    outputs=[gr.Textbox(label="Caption")],
-                    title="Image Captioning with BLIP",
-                    description="Caption any image using the BLIP model",
-                    allow_flagging="never")
-                     
-ImageCaptionApp.launch()
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+model_id = "Salesforce/blip-image-captioning-base"
+
+model = BlipForConditionalGeneration.from_pretrained(model_id)
+processor = BlipProcessor.from_pretrained(model_id)
+
+def launch(input):
+    image = Image.open(requests.get(input, stream=True).raw).convert('RGB')
+    inputs = processor(image, return_tensors="pt")
+    out = model.generate(**inputs)
+    return processor.decode(out[0], skip_special_tokens=True)
+
+iface = gr.Interface(launch, inputs="text", outputs="text")
+iface.launch()