Update app.py

app.py

@@ -57,19 +57,27 @@ def inference(raw_image, model_n, question, strategy):
             answer = model_vq(image_vq, question, train=False, inference='generate') 
         return  'answer: '+answer[0]
     
-inputs = [
-    gr.Image(type='pil', interactive=True),
-    gr.inputs.Radio(choices=['Image Captioning',"Visual Question Answering"],
-    type="value",
-    default="Image Captioning",
-    label="Task"
-),gr.inputs.Textbox(lines=2, label="Question"),gr.inputs.Radio(choices=['Beam search','Nucleus sampling'], type="value", default="Nucleus sampling", label="Caption Decoding Strategy")]
-outputs = gr.outputs.Textbox(label="Output")
+inputs = [gr.Image(type='pil'), 
+          gr.Radio(choices=['Image Captioning',"Visual Question Answering"], type="value", value="Image Captioning", label="Task"),
+          gr.Textbox(lines=2, label="Question"),
+          gr.Radio(choices=['Beam search','Nucleus sampling'], type="value", value="Nucleus sampling", label="Caption Decoding Strategy")]
+outputs = gr.Textbox(label="Output")
 
 title = "BLIP"
 
-description = "Gradio demo for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (Salesforce Research). We have now disable image uploading as of March 23. 2023. Click one of the examples to load them. Read more at the links below."
+description = "Gradio demo for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (Salesforce Research). To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
 
-article = """<p style='text-align: center'><a href='https://arxiv.org/abs/2201.12086' target='_blank'>BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation</a> | <a href='https://github.com/salesforce/BLIP' target='_blank'>Github Repo</a></p>"""
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.12086' target='_blank'>BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation</a> | <a href='https://github.com/salesforce/BLIP' target='_blank'>Github Repo</a></p>"
 
-gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=[['starrynight.jpeg',"Image Captioning","None","Nucleus sampling"]]).launch(enable_queue=True)
+
+demo = gr.Interface(inference, 
+                    inputs, 
+                    outputs, 
+                    title=title, 
+                    description=description, 
+                    article=article, 
+                    examples=[['starrynight.jpeg',"Image Captioning","None","Nucleus sampling"]],
+                    allow_flagging='never',
+                    cache_examples="lazy",
+                    delete_cache=(4000, 4000))
+demo.queue(default_concurrency_limit=1).launch(show_error=True, show_api=True, mcp_server=True)