Create app.py

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
+
+# Load the BLIP model and processor
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def generate_caption(image):
+    image = image.convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        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", label="Upload an Image"),
+    outputs=gr.Textbox(label="Generated Caption"),
+    title="📸 BLIP Image Captioning",
+    description="Upload an image and get a descriptive caption using the BLIP model.",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    interface.launch()