Update app.py

app.py

@@ -1,24 +1,21 @@
 import gradio as gr
 import os
-
-# Load model directly
 from transformers import AutoProcessor, AutoModelForImageTextToText
 
+# Load model and processor
 processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-base")
 
-
 def caption(image):
-    inputs = processor(image,return_tensors="pt")
+    # 'image' is now a PIL Image object because of type="pil"
+    inputs = processor(image, return_tensors="pt")
     out = model.generate(**inputs)
-
     return processor.decode(out[0], skip_special_tokens=True)
 
 demo = gr.Interface(
-    fn = caption,
-    inputs = gr.Image(label = "Upload Image", type = "filepath"),
-    outputs = "text"
+    fn=caption,
+    inputs=gr.Image(label="Upload Image", type="pil"), 
+    outputs="text"
 )
 
-demo.launch(share=True, 
-             server_port=int(os.environ['PORT1']))
+demo.launch()