caption.py

app.py

@@ -0,0 +1,15 @@
+# app.py
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def caption_image(image):
+    inputs = processor(images=image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
+
+gr.Interface(fn=caption_image, inputs=gr.Image(), outputs="text").launch()