Update app.py

app.py

@@ -1,12 +1,18 @@
 import gradio as gr
 from groq import Groq
 import os
-import matplotlib.pyplot as plt
-import numpy as np
 
 # Initialize Groq client with your API key
 client = Groq(api_key=os.environ["GROQ_API_KEY"])
 
+# Load Text-to-Image Models
+model1 = gr.load("models/prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA")
+model2 = gr.load("models/Purz/face-projection")
+
+# Stop event for threading (image generation)
+stop_event = threading.Event()
+
+# Function to generate tutor output (lesson, question, feedback)
 def generate_tutor_output(subject, difficulty, student_input):
     prompt = f"""
     You are an expert tutor in {subject} at the {difficulty} level. 
@@ -37,28 +43,31 @@ def generate_tutor_output(subject, difficulty, student_input):
     
     return completion.choices[0].message.content
 
-# Function to generate a simple graph (e.g., bar chart)
-def generate_graph():
-    # Example data
-    x = ['A', 'B', 'C', 'D']
-    y = [10, 20, 15, 25]
-    
-    fig, ax = plt.subplots()
-    ax.bar(x, y)
-    ax.set_title("Example Bar Chart")
-    ax.set_xlabel("Categories")
-    ax.set_ylabel("Values")
-    
-    # Save the plot to a file
-    plt.tight_layout()
-    plt.savefig("/tmp/bar_chart.png")  # Save to temp directory
-    plt.close(fig)
-    
-    return "/tmp/bar_chart.png"  # Return the path to the saved image
+# Function to generate images based on model selection
+def generate_images(text, selected_model):
+    stop_event.clear()
+
+    if selected_model == "Model 1 (Turbo Realism)":
+        model = model1
+    elif selected_model == "Model 2 (Face Projection)":
+        model = model2
+    else:
+        return ["Invalid model selection."] * 3
+
+    results = []
+    for i in range(3):
+        if stop_event.is_set():
+            return ["Image generation stopped by user."] * 3
+
+        modified_text = f"{text} variation {i+1}"
+        result = model(modified_text)
+        results.append(result)
+
+    return results
 
 # Set up the Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# 🎓 Your AI Tutor")
+    gr.Markdown("# 🎓 Your AI Tutor with Visuals & Images")
     
     with gr.Row():
         with gr.Column(scale=2):
@@ -78,38 +87,46 @@ with gr.Blocks() as demo:
                 label="Your Input", 
                 info="Enter the topic you want to learn"
             )
-            submit_button = gr.Button("Generate Lesson", variant="primary")
+            model_selector = gr.Radio(
+                ["Model 1 (Turbo Realism)", "Model 2 (Face Projection)"],
+                label="Select Image Generation Model",
+                value="Model 1 (Turbo Realism)"
+            )
+            submit_button = gr.Button("Generate Lesson & Images", variant="primary")
         
         with gr.Column(scale=3):
-            # Output fields for lesson, question, and feedback
+            # Output fields for lesson, question, feedback, and images
             lesson_output = gr.Markdown(label="Lesson")
             question_output = gr.Markdown(label="Comprehension Question")
             feedback_output = gr.Markdown(label="Feedback")
-            graph_output = gr.Image(label="Generated Graph")
+            output1 = gr.Image(label="Generated Image 1")
+            output2 = gr.Image(label="Generated Image 2")
+            output3 = gr.Image(label="Generated Image 3")
     
     gr.Markdown("""
     ### How to Use
     1. Select a subject from the dropdown.
     2. Choose your difficulty level.
     3. Enter the topic or question you'd like to explore.
-    4. Click 'Generate Lesson' to receive a personalized lesson, question, and feedback.
-    5. The AI will also generate a simple bar chart as a visual representation.
+    4. Choose the model for image generation.
+    5. Click 'Generate Lesson & Images' to receive a personalized lesson, question, feedback, and images.
     6. Review the AI-generated content to enhance your learning.
     7. Feel free to ask follow-up questions or explore new topics!
     """)
     
-    def process_output(output):
+    def process_output(subject, difficulty, student_input, selected_model):
         try:
-            parsed = eval(output)  # Convert string to dictionary
-            graph_path = generate_graph()  # Generate graph
-            return parsed["lesson"], parsed["question"], parsed["feedback"], graph_path
+            tutor_output = generate_tutor_output(subject, difficulty, student_input)
+            parsed = eval(tutor_output)  # Convert string to dictionary
+            images = generate_images(student_input, selected_model)  # Generate images
+            return parsed["lesson"], parsed["question"], parsed["feedback"], images[0], images[1], images[2]
         except:
-            return "Error parsing output", "No question available", "No feedback available", None
+            return "Error parsing output", "No question available", "No feedback available", None, None, None
     
     submit_button.click(
-        fn=lambda s, d, i: process_output(generate_tutor_output(s, d, i)),
-        inputs=[subject, difficulty, student_input],
-        outputs=[lesson_output, question_output, feedback_output, graph_output]
+        fn=process_output,
+        inputs=[subject, difficulty, student_input, model_selector],
+        outputs=[lesson_output, question_output, feedback_output, output1, output2, output3]
     )
 
 if __name__ == "__main__":