Update main.py

main.py

@@ -60,7 +60,7 @@ examples = [["cat.jpg"], ["dog.jpg"], ["horse.jpg"]]
 outputs = [gr.outputs.Textbox(label="Caption generated by GIT-base"), gr.outputs.Textbox(label="Caption generated by GIT-large"), gr.outputs.Textbox(label="Caption generated by BLIP-base"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by ViT+GPT-2")] 
 
 title = "Image to Text : Multiple Models"
-description = "Gradio Demo to compare GIT, BLIP and ViT+GPT2, 3 state-of-the-art vision+language models. To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below."
+description = "Explore the Gradio Demo for comparing three state-of-the-art vision+language models: GIT, BLIP, and ViT+GPT2. To use the demo, upload your image and click 'submit,' or choose from the provided examples."
 article = "<p style='text-align: center'><a href='https://huggingface.co/docs/transformers/main/model_doc/blip' target='_blank'>BLIP docs</a> | <a href='https://huggingface.co/docs/transformers/main/model_doc/git' target='_blank'>GIT docs</a></p>"
 
 iface = gr.Interface(fn=generate_captions,