Update app.py

Add new diffusion model as the image gen

app.py

@@ -1,69 +1,87 @@
-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
+import torch
+from diffusers import StableDiffusionPipeline
+from pathlib import Path
+from typing import Optional
 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 !
 @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 generate_image_tool(
+    prompt: str,
+    model_name: str = "stabilityai/stable-diffusion-2-1",
+    num_inference_steps: int = 50,
+    output_path: str = "generated_image.png"
+) -> str:
+    """A tool for generating images from text prompts using Stable Diffusion.
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        prompt: Text description of the image (must be SFW)
+        model_name: AI model to use (default: stabilityai/stable-diffusion-2-1)
+        num_inference_steps: Quality steps (20-100)
+        output_path: Where to save the image
     """
-    return "What magic will you build ?"
+    # Safety check
+    unsafe_keywords = ["nude", "porn", "explicit", "adult", "nsfw"]
+    if any(kw in prompt.lower() for kw in unsafe_keywords):
+        return "Error: Content policy violation detected in prompt"
+
+    try:
+        pipe = StableDiffusionPipeline.from_pretrained(
+            model_name,
+            torch_dtype=torch.float16
+        ).to("cuda")
+        
+        image = pipe(
+            prompt=prompt,
+            num_inference_steps=num_inference_steps
+        ).images[0]
+        
+        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
+        image.save(output_path)
+        return f"Image generated successfully at: {output_path}"
+        
+    except Exception as e:
+        return f"Image generation failed: {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').
+        timezone: A valid timezone (e.g., 'America/New_York')
     """
     try:
-        # Create timezone object
         tz = pytz.timezone(timezone)
-        # Get current time in that timezone
         local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
-        return f"The current local time in {timezone} is: {local_time}"
+        return f"Current time in {timezone}: {local_time}"
     except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
-
+        return f"Error: {str(e)}"
 
 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 = 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=0.5,
+    model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
+    custom_role_conversions=None,
 )
 
-
-# Import tool from Hub
-image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
-
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
     
 agent = CodeAgent(
     model=model,
-    tools=[image_generation_tool,final_answer], ## add your tools here (don't remove final answer)
+    tools=[generate_image_tool, get_current_time_in_timezone, final_answer],
     max_steps=6,
     verbosity_level=1,
+    prompt_templates=prompt_templates,
     grammar=None,
     planning_interval=None,
-    name=None,
-    description=None,
-    prompt_templates=prompt_templates
+    name="Creative Assistant",
+    description="AI assistant capable of generating images and providing time information"
 )
 
-
 GradioUI(agent).launch()