anime image generator

app.py

@@ -1,26 +1,69 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
-from tools.final_answer import FinalAnswerTool
-
+from tools.final_answer import FinalAnswerTool 
 from Gradio_UI import GradioUI
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
+# Enhanced custom tool for anime image generation
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
+def anime_image_generator(description: str, style: str = "anime") -> str:
+    """A tool that generates anime-style images based on user descriptions.
+    
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        description: Detailed description of the anime image to generate
+        style: Style modifier (default: "anime", options: "anime", "manga", "kawaii", "realistic_anime")
     """
-    return "What magic will you build ?"
+    try:
+        # Enhance the prompt with anime-specific keywords
+        anime_keywords = {
+            "anime": "anime style, high quality, detailed, vibrant colors, japanese animation style",
+            "manga": "manga style, black and white, detailed lineart, dramatic shading",
+            "kawaii": "kawaii style, cute, adorable, pastel colors, chibi proportions",
+            "realistic_anime": "realistic anime style, detailed face, expressive eyes, high resolution"
+        }
+        
+        style_prompt = anime_keywords.get(style, anime_keywords["anime"])
+        enhanced_description = f"{description}, {style_prompt}, masterpiece, best quality"
+        
+        return f"Generated anime image with description: '{enhanced_description}' in {style} style"
+    except Exception as e:
+        return f"Error generating anime image: {str(e)}"
+
+@tool
+def analyze_image_description(user_input: str) -> str:
+    """A tool that analyzes and enhances user input for better anime image generation.
+    
+    Args:
+        user_input: Raw user description of desired image
+    """
+    try:
+        # Common anime elements to suggest or enhance
+        anime_elements = [
+            "character appearance", "clothing style", "background setting", 
+            "mood/atmosphere", "art style", "color palette", "special effects"
+        ]
+        
+        analysis = f"Analyzing description: '{user_input}'\n"
+        analysis += "Suggested enhancements for anime generation:\n"
+        
+        # Basic analysis and suggestions
+        if "character" in user_input.lower() or "person" in user_input.lower():
+            analysis += "- Consider adding details about hair color, eye color, clothing style\n"
+        if "background" not in user_input.lower():
+            analysis += "- Consider adding background setting (school, forest, city, etc.)\n"
+        if "color" not in user_input.lower():
+            analysis += "- Consider specifying color palette preferences\n"
+            
+        return analysis
+    except Exception as e:
+        return f"Error analyzing description: {str(e)}"
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
     """A tool that fetches the current local time in a specified timezone.
+    
     Args:
         timezone: A string representing a valid timezone (e.g., 'America/New_York').
     """
@@ -33,37 +76,86 @@ def get_current_time_in_timezone(timezone: str) -> str:
     except Exception as e:
         return f"Error fetching time for timezone '{timezone}': {str(e)}"
 
+@tool
+def enhance_anime_prompt(base_description: str, character_details: str = "", background: str = "", mood: str = "") -> str:
+    """A tool that creates a comprehensive anime image prompt by combining various elements.
+    
+    Args:
+        base_description: Basic description of the desired image
+        character_details: Optional character-specific details (hair, eyes, clothing, etc.)
+        background: Optional background setting description
+        mood: Optional mood or atmosphere description
+    """
+    try:
+        enhanced_prompt = base_description
+        
+        if character_details:
+            enhanced_prompt += f", {character_details}"
+        if background:
+            enhanced_prompt += f", background: {background}"
+        if mood:
+            enhanced_prompt += f", mood: {mood}"
+            
+        # Add quality and style modifiers
+        enhanced_prompt += ", anime style, high quality, detailed artwork, vibrant colors, professional illustration"
+        
+        return f"Enhanced anime prompt: {enhanced_prompt}"
+    except Exception as e:
+        return f"Error enhancing prompt: {str(e)}"
 
+# Initialize tools
 final_answer = FinalAnswerTool()
 
-# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
-# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
-
+# Model configuration - using Qwen for better code generation and reasoning
 model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-custom_role_conversions=None,
+    max_tokens=2096,
+    temperature=0.7,  # Slightly higher for more creative image descriptions
+    model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
+    custom_role_conversions=None,
 )
 
+# Import image generation tool from Hub
+try:
+    image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
+    print("Successfully loaded image generation tool")
+except Exception as e:
+    print(f"Warning: Could not load image generation tool: {e}")
+    image_generation_tool = None
 
-# Import tool from Hub
-image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
-
+# Load prompt templates
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
-    
+
+# Create the agent with anime-focused tools
+tools_list = [
+    final_answer,
+    anime_image_generator,
+    analyze_image_description,
+    enhance_anime_prompt,
+    get_current_time_in_timezone
+]
+
+# Add the image generation tool if it loaded successfully
+if image_generation_tool:
+    tools_list.append(image_generation_tool)
+
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
-    max_steps=6,
+    tools=tools_list,
+    max_steps=8,  # Increased steps for more complex image generation workflows
     verbosity_level=1,
     grammar=None,
     planning_interval=None,
-    name=None,
-    description=None,
+    name="AnimeImageGenerator",
+    description="An AI agent specialized in generating anime-style images based on user descriptions",
     prompt_templates=prompt_templates
 )
 
-
-GradioUI(agent).launch()
+# Launch the Gradio interface
+if __name__ == "__main__":
+    print("Starting Anime Image Generator...")
+    print("Available tools:")
+    for tool in tools_list:
+        print(f"- {tool.name}")
+    
+    GradioUI(agent).launch()