Update app.py

app.py

@@ -1,31 +1,37 @@
-import torch
-from transformers import pipeline, AutoProcessor, AutoModelForVision2Seq
-from PIL import Image
-import gradio as gr
-
-# Automatically use GPU if available
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-# Load processor and model
-processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip-image-captioning-large").to(device)
-
-# Inference function
-def generate_caption(image):
-    image = image.convert("RGB")
-    inputs = processor(images=image, return_tensors="pt").to(device)
-    output = model.generate(**inputs)
-    caption = processor.decode(output[0], skip_special_tokens=True)
-    return caption
-
-# Gradio interface
-interface = gr.Interface(
-    fn=generate_caption,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="🖼️ Image to Text Captioning",
-    description="Upload an image and get a caption using BLIP (Salesforce/blip-image-captioning-large)."
-)
-
-if __name__ == "__main__":
-    interface.launch()
+import torch
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from PIL import Image
+import gradio as gr
+
+# Device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load processor & model
+processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = AutoModelForVision2Seq.from_pretrained(
+    "Salesforce/blip-image-captioning-large"
+).to(device)
+
+# Inference function
+def generate_caption(image):
+    try:
+        image = image.convert("RGB")
+        with torch.inference_mode():
+            inputs = processor(images=image, return_tensors="pt").to(device)
+            output = model.generate(**inputs)
+        caption = processor.decode(output[0], skip_special_tokens=True)
+        return caption
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Gradio UI
+interface = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="🖼️ Image to Text Captioning",
+    description="Upload an image and get a caption using BLIP (Salesforce/blip-image-captioning-large)."
+)
+
+if __name__ == "__main__":
+    interface.launch(share=True)