Update app.py

app.py

@@ -44,10 +44,10 @@ def zero_shot(image, text_input):
     
 with gr.Blocks() as demo: 
     gr.Markdown( """
-    Input voice/text 
-    Convert voice/text to image via Latent Diffusion
-    Given list of labels and a selected image from gallery do zero-shot classification 
-    Coming soon: TTS(audio) your output label as: Your output looks like "label of zero-shot"
+    - [x] Input voice/text 
+    - [x] Convert voice/text to image via Latent Diffusion
+    - [x] Given list of labels and a selected image from gallery do zero-shot classification 
+    - [ ] Coming soon: TTS(audio) your output label as: Your output looks like "label of zero-shot"
      """)    
     with gr.Row():
         with gr.Column():
@@ -75,7 +75,7 @@ with gr.Blocks() as demo:
 
         
     speech_to_text.click(speech_to_text, inputs=audio_file, outputs=text)
-    get_image_latent.click(text2image_latent, inputs=[text,steps,width,height,images,diversity], outputs=gallery)
-    zero_shot_clf.click(zero_shot, inputs=[gallery,text_input], outputs=label)
-
-demo.launch(enable_queue=False)
+    get_image_latent.click(text2image_latent, inputs=[text, steps, width, height, images, diversity], outputs=gallery)
+    zero_shot_clf.click(zero_shot, inputs=[gallery, text_input], outputs=label)  
+      
+demo.launch()