diff --git a/README.md b/README.md
index 7adf1d0..498cc8f 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # MooseCP Image Server
 
-A Model Context Protocol (MCP) server designed to provide LLMs with efficient, token-optimized visual access to image directories. Instead of dumping full-resolution images (which waste tokens and cause context overflow), MooseCP provides a hierarchical workflow: **List $\rightarrow$ Scan $\rightarrow$ Preview $\rightarrow$ Inspect**.
+A Model Context Protocol (MCP) server designed to provide LLMs with efficient, token-optimized visual access to image directories and AI generation capabilities. Instead of dumping full-resolution images (which waste tokens and cause context overflow), MooseCP provides a hierarchical workflow: **List $\rightarrow$ Scan $\rightarrow$ Preview $\rightarrow$ Inspect**.
 
 ## ⚠️ AI SLOP DISCLAIMER
 This entire project was vibe-coded by an AI. It is 100% slop code. Use it at your own risk.
@@ -32,6 +32,17 @@ Extracts AI generation parameters from PNG files.
 Returns the full-resolution image.
 *   **Best for**: Final confirmation or deep visual analysis where every pixel counts.
 
+### 🎨 `generate_image`
+Triggers an image generation on a local Stable Diffusion WebUI Forge instance.
+*   **Workflow**: Always call `get_model_info` first to determine the correct prompting style (e.g., tag-based vs. natural language).
+*   **Features**: Supports model-specific presets, resolution presets, and standard parameter overrides.
+*   **Output**: Returns a Base64 image for AI analysis and a proxy URL for direct embedding in the chat.
+
+### ℹ️ `get_model_info`
+Provides the "manual" for available generation models.
+*   **Best for**: Learning the prompting style, recommended settings, and available resolution presets for a specific model.
+*   **Workflow**: Call without arguments to see the catalog; call with `model_name` for the detailed guide.
+
 ### 🌐 `browse_wikipedia`
 Allows the model to browse Wikipedia using its API.
 *   **Best for**: Quickly retrieving summaries, structural maps (ToC), or specific section content from Wikipedia without dumping the entire page.
@@ -47,9 +58,10 @@ This server requires Python 3.10+ and the following packages:
 *   `uvicorn`: ASGI server for the SSE transport.
 *   `starlette`: Lightweight ASGI framework.
 *   `Pillow`: Image processing and thumbnail generation.
+*   `requests`: For communicating with the Stable Diffusion API.
 
 ```bash
-pip install uvicorn starlette Pillow
+pip install uvicorn starlette Pillow requests
 ```
 
 ### Setup
diff --git a/config.py b/config.py
index fbb731f..8cb5f3f 100644
--- a/config.py
+++ b/config.py
@@ -1,12 +1,22 @@
 import logging
+from pathlib import Path
+
+# --- Project Root ---
+# Get the directory where config.py is located
+ROOT_DIR = Path(__file__).parent.resolve()
 
 # --- Server & Logs ---
 HOST = "127.0.0.1"
 PORT = 8000
 LOG_LEVEL = "WARNING" # Options: "DEBUG", "INFO", "WARNING", "ERROR"
-LOG_FILE = "debug.log"
+LOG_FILE = str(ROOT_DIR / "debug.log")
 USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64; rv:151.0) Gecko/20100101 Firefox/151.0" # Stealth User-Agent to bypass Wikipedia's bot detection
 
+# --- Stable Diffusion Config ---
+SD_URL = "http://127.0.0.1:7860"
+MODEL_PRESETS_PATH = str(ROOT_DIR / "model_presets.toml")
+RES_PRESETS_PATH = str(ROOT_DIR / "resolution_presets.toml")
+
 # --- Model Specific Token Tuning (Tuned for Gemma 4) ---
 # Patch size is typically (clip.vision.patch_size * n_merge)
 # For Gemma 4, this is 48px.
diff --git a/tools/generate_image.py b/tools/generate_image.py
index 3809100..1464e9b 100644
--- a/tools/generate_image.py
+++ b/tools/generate_image.py
@@ -1,23 +1,8 @@
 import requests
-import tomllib
-import os
 import base64
 import config
 from typing import Any, Dict, List
-from tools.utils import ToolError
-
-# Paths to config files
-MODEL_PRESETS_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "model_presets.toml")
-RES_PRESETS_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resolution_presets.toml")
-
-SD_URL = "http://127.0.0.1:7860"
-
-def load_toml(path: str) -> Dict[str, Any]:
-    try:
-        with open(path, "rb") as f:
-            return tomllib.load(f)
-    except Exception as e:
-        raise ToolError(f"Failed to load config file {path}: {str(e)}")
+from tools.utils import ToolError, load_toml
 
 async def handle(args: Dict[str, Any]) -> List[Dict[str, Any]]:
     """
@@ -34,7 +19,7 @@ async def handle(args: Dict[str, Any]) -> List[Dict[str, Any]]:
 
     # 2. FETCH CURRENT SERVER DEFAULTS & MAP LABELS
     try:
-        info_resp = requests.get(f"{SD_URL}/info", timeout=10)
+        info_resp = requests.get(f"{config.SD_URL}/info", timeout=10)
         info_resp.raise_for_status()
         info_data = info_resp.json()
         params_info = info_data["named_endpoints"]["/txt2img"]["parameters"]
@@ -62,8 +47,8 @@ async def handle(args: Dict[str, Any]) -> List[Dict[str, Any]]:
         label_map[mapped_label] = idx
 
     # 3. LOAD CONFIGS
-    models_cfg = load_toml(MODEL_PRESETS_PATH)
-    res_cfg = load_toml(RES_PRESETS_PATH)
+    models_cfg = load_toml(config.MODEL_PRESETS_PATH)
+    res_cfg = load_toml(config.RES_PRESETS_PATH)
     
     if model_name not in models_cfg:
         raise ToolError(f"Model '{model_name}' not found in presets. Available: {', '.join(models_cfg.keys())}")
diff --git a/tools/get_model_info.py b/tools/get_model_info.py
index 7190c60..5c5f613 100644
--- a/tools/get_model_info.py
+++ b/tools/get_model_info.py
@@ -1,18 +1,7 @@
-import tomllib
-import os
-from typing import Any, Dict, Union, List
-from tools.utils import ToolError
-
-# Paths to config files
-MODEL_PRESETS_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "model_presets.toml")
-RES_PRESETS_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "resolution_presets.toml")
-
-def load_toml(path: str) -> Dict[str, Any]:
-    try:
-        with open(path, "rb") as f:
-            return tomllib.load(f)
-    except Exception as e:
-        raise ToolError(f"Failed to load config file {path}: {str(e)}")
+import requests
+from typing import Any, Dict, List
+import config
+from tools.utils import ToolError, load_toml
 
 async def handle(args: Dict[str, Any]) -> Dict[str, Any]:
     """
@@ -20,8 +9,8 @@ async def handle(args: Dict[str, Any]) -> Dict[str, Any]:
     """
     model_name = args.get("model_name")
     
-    models = load_toml(MODEL_PRESETS_PATH)
-    res_presets = load_toml(RES_PRESETS_PATH)
+    models = load_toml(config.MODEL_PRESETS_PATH)
+    res_presets = load_toml(config.RES_PRESETS_PATH)
     
     if not model_name:
         # Return a catalog of all models
diff --git a/tools/utils.py b/tools/utils.py
index f9bc4d7..ad35198 100644
--- a/tools/utils.py
+++ b/tools/utils.py
@@ -1,5 +1,6 @@
 import time
 import datetime
+import tomllib
 from pathlib import Path
 from typing import List, Dict, Any, Optional
 
@@ -8,6 +9,14 @@ class ToolError(Exception):
     """Custom exception for tool-related errors to be caught by the MCP server."""
     pass
 
+def load_toml(path: str) -> Dict[str, Any]:
+    """Loads a TOML file into a dictionary."""
+    try:
+        with open(path, "rb") as f:
+            return tomllib.load(f)
+    except Exception as e:
+        raise ToolError(f"Failed to load config file {path}: {str(e)}")
+
 def format_relative_time(timestamp: float) -> str:
     """Converts a timestamp to a human-readable relative format."""
     now = time.time()