Update app.py

app.py

@@ -1,46 +1,76 @@
-#%% Import libraries
 from transformers import load_tool, ReactCodeAgent, HfApiEngine
-from PIL import Image
-import torch
-import numpy as np
+from PIL import Image, ImageDraw, ImageFont
 import tempfile
-import os
-import uuid
 import gradio as gr
 
-
-#%% Methods 
-# function to plot and save an AgentImage
-def plot_and_save_agent_image(agent_image, save_path=None):
+#%% Methods
+# Function to add a label to an image
+def add_label_to_image(image, label):
+    # Create a drawing context
+    draw = ImageDraw.Draw(image)
+    
+    # Define font size and color (adjust font path for your environment)
+    font_path = "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf"  # Example font path
+    font_size = 40
+    try:
+        font = ImageFont.truetype(font_path, font_size)
+    except:
+        font = ImageFont.load_default()
+    
+    # Get the text size and position
+    text_size = draw.textsize(label, font=font)
+    position = ((image.width - text_size[0]) // 2, image.height - text_size[1] - 10)  # Centered at the bottom
+    
+    # Add a semi-transparent rectangle behind the text for better visibility
+    rect_margin = 10
+    rect_position = [
+        position[0] - rect_margin,
+        position[1] - rect_margin,
+        position[0] + text_size[0] + rect_margin,
+        position[1] + text_size[1] + rect_margin,
+    ]
+    draw.rectangle(rect_position, fill=(0, 0, 0, 128))  # Semi-transparent black
+    draw.text(position, label, fill="white", font=font)
+    return image
+
+# Function to plot, label, and save an image
+def plot_and_save_agent_image(agent_image, label, save_path=None):
     # Convert AgentImage to a raw PIL Image
     pil_image = agent_image.to_raw()
 
+    # Add a label to the image
+    labeled_image = add_label_to_image(pil_image, label)
+
     # Plot the image using PIL's show method
-    pil_image.show()
+    labeled_image.show()
 
     # If save_path is provided, save the image
     if save_path:
-        pil_image.save(save_path)
+        labeled_image.save(save_path)
         print(f"Image saved to {save_path}")
     else:
         print("No save path provided. Image not saved.")
 
-
+# Function to generate prompts for an object
 def generate_prompts_for_object(object_name):
     prompts = {
         "past": f"Show an old version of a {object_name} from its early days.",
-        "present": f"Show a {object_name} with from present with current features/design/technology.",
+        "present": f"Show a {object_name} with current features/design/technology.",
         "future": f"Show a futuristic version of a {object_name}, by predicting advanced features and futuristic design."
     }
     return prompts
 
-
-# Function to generate the car industry history
+# Function to generate the object's history images and GIF
 def generate_object_history(object_name):
     images = []
     
     # Get prompts for the object
     prompts = generate_prompts_for_object(object_name)
+    labels = {
+        "past": "Past Concept",
+        "present": "Present Concept",
+        "future": "Future Concept"
+    }
     
     # Generate sequential images and display them
     for time_period, frame in prompts.items():
@@ -50,10 +80,9 @@ def generate_object_history(object_name):
         # Append the image to the list for GIF creation
         images.append(result.to_raw())  # Ensure we're using raw image for GIF
 
-        # Save each image with the appropriate name (past, present, future)
+        # Save each image with the appropriate name and label
         image_filename = f"{object_name}_{time_period}.png"
-        plot_and_save_agent_image(result, save_path=image_filename)
-        
+        plot_and_save_agent_image(result, labels[time_period], save_path=image_filename)
         
     # Create GIF from images
     gif_path = f"{object_name}_evolution.gif"
@@ -68,25 +97,20 @@ def generate_object_history(object_name):
     # Return images and GIF path
     return images, gif_path
 
-
 #%% Initialization of tools and AI_Agent
-# Import text-to-image tool from Hub 
-# m-ric/text-to-image model generates images based on textual descriptions.
-image_generation_tool = load_tool("m-ric/text-to-image", cache=False) #cache=False ensures it fetches the latest tool updates directly from the Hub.
+# Import text-to-image tool from Hub
+image_generation_tool = load_tool("m-ric/text-to-image", cache=False)
 
 # Import search tool from LangChain
-#This tool allows the agent to search for and retrieve information from the web.
 from transformers.agents.search import DuckDuckGoSearchTool
-
 search_tool = DuckDuckGoSearchTool()
 
-# Qwen2.5-72B-Instruct is a specific, a LLM fine-tuned for instruction-following tasks.
-llm_engine = HfApiEngine("Qwen/Qwen2.5-72B-Instruct") 
+# Load the LLM engine
+llm_engine = HfApiEngine("Qwen/Qwen2.5-72B-Instruct")
+
 # Initialize the agent with both tools
 agent = ReactCodeAgent(tools=[image_generation_tool, search_tool], llm_engine=llm_engine)
 
-
-
 # Gradio interface
 def create_gradio_interface():
     with gr.Blocks() as demo:
@@ -124,11 +148,10 @@ def create_gradio_interface():
                 generate_button = gr.Button("Generate Evolution")
     
                 # Gradio Gallery component to display the images
-                image_gallery = gr.Gallery(label="Generated Images", show_label=True, columns=3, rows=1, 
-                                           value=default_images)
+                image_gallery = gr.Gallery(label="Generated Images", show_label=True, columns=3, rows=1)
 
                 # Output for the generated GIF
-                gif_output = gr.Image(label="Generated GIF", show_label=True, value=default_gif_path)
+                gif_output = gr.Image(label="Generated GIF", show_label=True)
          
         # Set the action when the button is clicked
         generate_button.click(fn=generate_object_history, inputs=[object_name_input], outputs=[image_gallery, gif_output])
@@ -137,6 +160,4 @@ def create_gradio_interface():
 
 # Launch the Gradio app 
 demo = create_gradio_interface()
-
-# To make it permanent and hosted, we can use Gradio's 'share' argument or host it on a server.
 demo.launch(share=True)