Update app.py

app.py

@@ -34,7 +34,7 @@ def generate_roast(image_path):
         model = genai.GenerativeModel(
             model_name="gemini-1.5-flash-002",
             generation_config=generation_config,
-            system_instruction="You are a professional satirist and fashion expert. You will be given a profile picture. Your duty is to roast in less than 50 words whatever is given to you in the funniest way possible!",
+            system_instruction="You are a professional satirist and fashion expert. Roast the provided profile picture in less than 50 words.",
         )
         
         chat_session = model.start_chat(
@@ -87,30 +87,29 @@ def generate_video(image_path, audio_path):
     except Exception as e:
         return f"Error generating video: {e}"
 
+# Function to process all steps at once
+def process_roast(image_path):
+    roast_text = generate_roast(image_path)
+    audio_path = text_to_speech(roast_text)
+    video_path = generate_video(image_path, audio_path)
+    return roast_text, audio_path, video_path
+
 # Gradio Interface
 with gr.Blocks(theme=theme) as demo:
-    gr.Markdown("# Image to Text-to-Speech Roasting App")
-    gr.Markdown("Upload an image, and the AI will roast it, convert the roast to audio, and create a video output.")
-    
+    gr.Markdown("# Image Roasting App with TTS and Video")
+    gr.Markdown("Upload an image, click 'Roast Image', and the AI will roast it, convert the roast to audio, and generate a video.")
+
     with gr.Row():
         image_input = gr.Image(type="filepath", label="Upload Image")
         
-    # Output areas
-    output_text = gr.Textbox(label="Roast Text")
-    audio_output = gr.Audio(label="Roast Audio")
-    video_output = gr.Video(label="Roast Video")
-
-    # Button to generate roast text
-    roast_button = gr.Button("Generate Roast Text")
-    roast_button.click(generate_roast, inputs=image_input, outputs=output_text)
-
-    # Button to generate audio from roast text
-    audio_button = gr.Button("Generate Roast Audio")
-    audio_button.click(text_to_speech, inputs=output_text, outputs=audio_output)
+        with gr.Column():
+            output_text = gr.Textbox(label="Roast Text")
+            audio_output = gr.Audio(label="Roast Audio")
+            video_output = gr.Video(label="Roast Video")
 
-    # Button to generate video from image and audio
-    video_button = gr.Button("Generate Roast Video")
-    video_button.click(generate_video, inputs=[image_input, audio_output], outputs=video_output)
+    # Single button to handle all actions
+    roast_button = gr.Button("Roast Image")
+    roast_button.click(process_roast, inputs=image_input, outputs=[output_text, audio_output, video_output])
 
 # Launch the app
 demo.launch(debug=True)