awslabs.nova-canvas-mcp-server 0.1.10652__tar.gz → 0.1.62303__tar.gz

awslabs_nova_canvas_mcp_server-0.1.62303/.python-version

@@ -0,0 +1 @@
+3.10

awslabs_nova_canvas_mcp_server-0.1.62303/Dockerfile

@@ -0,0 +1,29 @@
+# Generated by https://smithery.ai. See: https://smithery.ai/docs/config#dockerfile
+FROM python:3.10-alpine
+
+# Install build dependencies
+RUN apk add --no-cache gcc musl-dev linux-headers
+
+WORKDIR /app
+
+# Copy the entire repository (monorepo context)
+COPY . .
+
+# Set working directory to the MCP server subdirectory
+WORKDIR /app/src/nova-canvas-mcp-server
+
+# Create dummy AWS credentials to satisfy boto3 when using the default profile
+RUN mkdir -p /root/.aws && \
+    echo "[default]" > /root/.aws/credentials && \
+    echo "aws_access_key_id = dummy" >> /root/.aws/credentials && \
+    echo "aws_secret_access_key = dummy" >> /root/.aws/credentials
+
+# Upgrade pip and install the package
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir .
+
+# Expose port if using SSE transport (optional)
+EXPOSE 8888
+
+# Start the MCP server (entrypoint provided by project.scripts in pyproject.toml)
+CMD ["awslabs.nova-canvas-mcp-server"]

awslabs_nova_canvas_mcp_server-0.1.62303/PKG-INFO

@@ -0,0 +1,91 @@
+Metadata-Version: 2.4
+Name: awslabs.nova-canvas-mcp-server
+Version: 0.1.62303
+Summary: An AWS Labs Model Context Protocol (MCP) server for Amazon Nova Canvas
+Requires-Python: >=3.10
+Requires-Dist: boto3>=1.37.24
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: mcp[cli]>=1.6.0
+Requires-Dist: pydantic>=2.11.1
+Description-Content-Type: text/markdown
+
+# Amazon Nova Canvas MCP Server
+
+[![smithery badge](https://smithery.ai/badge/@awslabs/nova-canvas-mcp-server)](https://smithery.ai/server/@awslabs/nova-canvas-mcp-server)
+
+MCP server for generating images using Amazon Nova Canvas
+
+## Features
+
+### Text-based image generation
+
+- Create images from text prompts with `generate_image`
+- Customizable dimensions (320-4096px), quality options, and negative prompting
+- Supports multiple image generation (1-5) in single request
+- Adjustable parameters like cfg_scale (1.1-10.0) and seeded generation
+
+### Color-guided image generation
+
+- Generate images with specific color palettes using `generate_image_with_colors`
+- Define up to 10 hex color values to influence the image style and mood
+- Same customization options as text-based generation
+
+### Workspace integration
+
+- Images saved to user-specified workspace directories with automatic folder creation
+
+### AWS authentication
+
+- Uses AWS profiles for secure access to Amazon Nova Canvas services
+
+## Prerequisites
+
+1. Install `uv` from [Astral](https://docs.astral.sh/uv/getting-started/installation/) or the [GitHub README](https://github.com/astral-sh/uv#installation)
+2. Install Python using `uv python install 3.10`
+3. Set up AWS credentials with access to Amazon Bedrock and Nova Canvas
+   - You need an AWS account with Amazon Bedrock and Amazon Nova Canvas enabled
+   - Configure AWS credentials with `aws configure` or environment variables
+   - Ensure your IAM role/user has permissions to use Amazon Bedrock and Nova Canvas
+
+## Installation
+
+Here are some ways you can work with MCP across AWS, and we'll be adding support to more products including Amazon Q Developer CLI soon: (e.g. for Amazon Q Developer CLI MCP, `~/.aws/amazonq/mcp.json`):
+
+```json
+{
+  "mcpServers": {
+    "awslabs.nova-canvas-mcp-server": {
+      "command": "uvx",
+      "args": ["awslabs.nova-canvas-mcp-server@latest"],
+      "env": {
+        "AWS_PROFILE": "your-aws-profile",
+        "AWS_REGION": "us-east-1",
+        "FASTMCP_LOG_LEVEL": "ERROR"
+      },
+      "disabled": false,
+      "autoApprove": []
+    }
+  }
+}
+```
+
+### Installing via Smithery
+
+To install Amazon Nova Canvas MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@awslabs/nova-canvas-mcp-server):
+
+```bash
+npx -y @smithery/cli install @awslabs/nova-canvas-mcp-server --client claude
+```
+
+### AWS Authentication
+
+The MCP server uses the AWS profile specified in the `AWS_PROFILE` environment variable. If not provided, it defaults to the "default" profile in your AWS configuration file.
+
+```json
+"env": {
+  "AWS_PROFILE": "your-aws-profile",
+  "AWS_REGION": "us-east-1"
+}
+```
+
+Make sure the AWS profile has permissions to access Amazon Bedrock and Amazon Nova Canvas. The MCP server creates a boto3 session using the specified profile to authenticate with AWS services. Your AWS IAM credentials remain on your local machine and are strictly used for using the Amazon Bedrock model APIs.

awslabs_nova_canvas_mcp_server-0.1.62303/README.md

@@ -0,0 +1,80 @@
+# Amazon Nova Canvas MCP Server
+
+[![smithery badge](https://smithery.ai/badge/@awslabs/nova-canvas-mcp-server)](https://smithery.ai/server/@awslabs/nova-canvas-mcp-server)
+
+MCP server for generating images using Amazon Nova Canvas
+
+## Features
+
+### Text-based image generation
+
+- Create images from text prompts with `generate_image`
+- Customizable dimensions (320-4096px), quality options, and negative prompting
+- Supports multiple image generation (1-5) in single request
+- Adjustable parameters like cfg_scale (1.1-10.0) and seeded generation
+
+### Color-guided image generation
+
+- Generate images with specific color palettes using `generate_image_with_colors`
+- Define up to 10 hex color values to influence the image style and mood
+- Same customization options as text-based generation
+
+### Workspace integration
+
+- Images saved to user-specified workspace directories with automatic folder creation
+
+### AWS authentication
+
+- Uses AWS profiles for secure access to Amazon Nova Canvas services
+
+## Prerequisites
+
+1. Install `uv` from [Astral](https://docs.astral.sh/uv/getting-started/installation/) or the [GitHub README](https://github.com/astral-sh/uv#installation)
+2. Install Python using `uv python install 3.10`
+3. Set up AWS credentials with access to Amazon Bedrock and Nova Canvas
+   - You need an AWS account with Amazon Bedrock and Amazon Nova Canvas enabled
+   - Configure AWS credentials with `aws configure` or environment variables
+   - Ensure your IAM role/user has permissions to use Amazon Bedrock and Nova Canvas
+
+## Installation
+
+Here are some ways you can work with MCP across AWS, and we'll be adding support to more products including Amazon Q Developer CLI soon: (e.g. for Amazon Q Developer CLI MCP, `~/.aws/amazonq/mcp.json`):
+
+```json
+{
+  "mcpServers": {
+    "awslabs.nova-canvas-mcp-server": {
+      "command": "uvx",
+      "args": ["awslabs.nova-canvas-mcp-server@latest"],
+      "env": {
+        "AWS_PROFILE": "your-aws-profile",
+        "AWS_REGION": "us-east-1",
+        "FASTMCP_LOG_LEVEL": "ERROR"
+      },
+      "disabled": false,
+      "autoApprove": []
+    }
+  }
+}
+```
+
+### Installing via Smithery
+
+To install Amazon Nova Canvas MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@awslabs/nova-canvas-mcp-server):
+
+```bash
+npx -y @smithery/cli install @awslabs/nova-canvas-mcp-server --client claude
+```
+
+### AWS Authentication
+
+The MCP server uses the AWS profile specified in the `AWS_PROFILE` environment variable. If not provided, it defaults to the "default" profile in your AWS configuration file.
+
+```json
+"env": {
+  "AWS_PROFILE": "your-aws-profile",
+  "AWS_REGION": "us-east-1"
+}
+```
+
+Make sure the AWS profile has permissions to access Amazon Bedrock and Amazon Nova Canvas. The MCP server creates a boto3 session using the specified profile to authenticate with AWS services. Your AWS IAM credentials remain on your local machine and are strictly used for using the Amazon Bedrock model APIs.

{awslabs_nova_canvas_mcp_server-0.1.10652 → awslabs_nova_canvas_mcp_server-0.1.62303}/awslabs/nova_canvas_mcp_server/__init__.py

@@ -1,3 +1,3 @@
 """awslabs.nova-canvas-mcp-server"""
 
-__version__ = "0.1.6"
+__version__ = '0.1.6'

{awslabs_nova_canvas_mcp_server-0.1.10652 → awslabs_nova_canvas_mcp_server-0.1.62303}/awslabs/nova_canvas_mcp_server/consts.py

@@ -1,11 +1,11 @@
 # Constants
-NOVA_CANVAS_MODEL_ID = "amazon.nova-canvas-v1:0"
+NOVA_CANVAS_MODEL_ID = 'amazon.nova-canvas-v1:0'
 DEFAULT_WIDTH = 1024
 DEFAULT_HEIGHT = 1024
-DEFAULT_QUALITY = "standard"
+DEFAULT_QUALITY = 'standard'
 DEFAULT_CFG_SCALE = 6.5
 DEFAULT_NUMBER_OF_IMAGES = 1
-DEFAULT_OUTPUT_DIR = "output"  # Default directory inside workspace_dir
+DEFAULT_OUTPUT_DIR = 'output'  # Default directory inside workspace_dir
 
 
 # Nova Canvas Prompt Best Practices

{awslabs_nova_canvas_mcp_server-0.1.10652 → awslabs_nova_canvas_mcp_server-0.1.62303}/awslabs/nova_canvas_mcp_server/models.py

@@ -15,8 +15,8 @@ class Quality(str, Enum):
         PREMIUM: Premium quality image generation with enhanced details.
     """
 
-    STANDARD = "standard"
-    PREMIUM = "premium"
+    STANDARD = 'standard'
+    PREMIUM = 'premium'
 
 
 class TaskType(str, Enum):
@@ -27,8 +27,8 @@ class TaskType(str, Enum):
         COLOR_GUIDED_GENERATION: Generate an image guided by both text and color palette.
     """
 
-    TEXT_IMAGE = "TEXT_IMAGE"
-    COLOR_GUIDED_GENERATION = "COLOR_GUIDED_GENERATION"
+    TEXT_IMAGE = 'TEXT_IMAGE'
+    COLOR_GUIDED_GENERATION = 'COLOR_GUIDED_GENERATION'
 
 
 class ImageGenerationConfig(BaseModel):
@@ -50,12 +50,10 @@ class ImageGenerationConfig(BaseModel):
     height: int = Field(default=1024, ge=320, le=4096)
     quality: Quality = Quality.STANDARD
     cfgScale: float = Field(default=6.5, ge=1.1, le=10.0)
-    seed: int = Field(
-        default_factory=lambda: random.randint(0, 858993459), ge=0, le=858993459
-    )
+    seed: int = Field(default_factory=lambda: random.randint(0, 858993459), ge=0, le=858993459)
     numberOfImages: int = Field(default=1, ge=1, le=5)
 
-    @field_validator("width", "height")
+    @field_validator('width', 'height')
     @classmethod
     def must_be_divisible_by_16(cls, v: int) -> int:
         """Validate that width and height are divisible by 16.
@@ -70,10 +68,10 @@ class ImageGenerationConfig(BaseModel):
             ValueError: If the value is not divisible by 16.
         """
         if v % 16 != 0:
-            raise ValueError("Value must be divisible by 16")
+            raise ValueError('Value must be divisible by 16')
         return v
 
-    @model_validator(mode="after")
+    @model_validator(mode='after')
     def validate_aspect_ratio_and_total_pixels(self):
         """Validate aspect ratio and total pixel count.
 
@@ -93,12 +91,12 @@ class ImageGenerationConfig(BaseModel):
         # Check aspect ratio between 1:4 and 4:1
         aspect_ratio = width / height
         if aspect_ratio < 0.25 or aspect_ratio > 4.0:
-            raise ValueError("Aspect ratio must be between 1:4 and 4:1")
+            raise ValueError('Aspect ratio must be between 1:4 and 4:1')
 
         # Check total pixel count
         total_pixels = width * height
         if total_pixels >= 4194304:
-            raise ValueError("Total pixel count must be less than 4,194,304")
+            raise ValueError('Total pixel count must be less than 4,194,304')
 
         return self
 
@@ -132,7 +130,7 @@ class ColorGuidedGenerationParams(BaseModel):
     text: str = Field(..., min_length=1, max_length=1024)
     negativeText: Optional[str] = Field(default=None, min_length=1, max_length=1024)
 
-    @field_validator("colors")
+    @field_validator('colors')
     @classmethod
     def validate_hex_colors(cls, v: List[str]) -> List[str]:
         """Validate that colors are in the correct hexadecimal format.
@@ -146,7 +144,7 @@ class ColorGuidedGenerationParams(BaseModel):
         Raises:
             ValueError: If any color is not a valid hexadecimal color in the format '#RRGGBB'.
         """
-        hex_pattern = re.compile(r"^#[0-9A-Fa-f]{6}$")
+        hex_pattern = re.compile(r'^#[0-9A-Fa-f]{6}$')
         for color in v:
             if not hex_pattern.match(color):
                 raise ValueError(
@@ -182,13 +180,13 @@ class TextImageRequest(BaseModel):
         """
         text_to_image_params = self.textToImageParams.model_dump()
         # Remove negativeText if it's None
-        if text_to_image_params.get("negativeText") is None:
-            text_to_image_params.pop("negativeText", None)
+        if text_to_image_params.get('negativeText') is None:
+            text_to_image_params.pop('negativeText', None)
 
         return {
-            "taskType": self.taskType,
-            "textToImageParams": text_to_image_params,
-            "imageGenerationConfig": self.imageGenerationConfig.model_dump()
+            'taskType': self.taskType,
+            'textToImageParams': text_to_image_params,
+            'imageGenerationConfig': self.imageGenerationConfig.model_dump()
             if self.imageGenerationConfig
             else None,
         }
@@ -206,9 +204,7 @@ class ColorGuidedRequest(BaseModel):
         imageGenerationConfig: Configuration for image generation.
     """
 
-    taskType: Literal[
-        TaskType.COLOR_GUIDED_GENERATION
-    ] = TaskType.COLOR_GUIDED_GENERATION
+    taskType: Literal[TaskType.COLOR_GUIDED_GENERATION] = TaskType.COLOR_GUIDED_GENERATION
     colorGuidedGenerationParams: ColorGuidedGenerationParams
     imageGenerationConfig: Optional[ImageGenerationConfig] = Field(
         default_factory=ImageGenerationConfig
@@ -223,13 +219,13 @@ class ColorGuidedRequest(BaseModel):
         """
         color_guided_params = self.colorGuidedGenerationParams.model_dump()
         # Remove negativeText if it's None
-        if color_guided_params.get("negativeText") is None:
-            color_guided_params.pop("negativeText", None)
+        if color_guided_params.get('negativeText') is None:
+            color_guided_params.pop('negativeText', None)
 
         return {
-            "taskType": self.taskType,
-            "colorGuidedGenerationParams": color_guided_params,
-            "imageGenerationConfig": self.imageGenerationConfig.model_dump()
+            'taskType': self.taskType,
+            'colorGuidedGenerationParams': color_guided_params,
+            'imageGenerationConfig': self.imageGenerationConfig.model_dump()
             if self.imageGenerationConfig
             else None,
         }

{awslabs_nova_canvas_mcp_server-0.1.10652 → awslabs_nova_canvas_mcp_server-0.1.62303}/awslabs/nova_canvas_mcp_server/novacanvas.py

@@ -41,7 +41,7 @@ def save_generated_images(
     base64_images: List[str],
     filename: Optional[str] = None,
     number_of_images: int = DEFAULT_NUMBER_OF_IMAGES,
-    prefix: str = "nova_canvas",
+    prefix: str = 'nova_canvas',
     workspace_dir: Optional[str] = None,
 ) -> Dict[str, List]:
     """Save base64-encoded images to files.
@@ -56,7 +56,7 @@ def save_generated_images(
     Returns:
         Dictionary with lists of paths to the saved image files and PIL Image objects.
     """
-    logger.debug(f"Saving {len(base64_images)} images")
+    logger.debug(f'Saving {len(base64_images)} images')
     # Determine the output directory
     if workspace_dir:
         output_dir = os.path.join(workspace_dir, DEFAULT_OUTPUT_DIR)
@@ -73,27 +73,25 @@ def save_generated_images(
         # Generate filename if not provided
         if filename:
             image_filename = (
-                f"{filename}_{i + 1}.png" if number_of_images > 1 else f"{filename}.png"
+                f'{filename}_{i + 1}.png' if number_of_images > 1 else f'{filename}.png'
             )
         else:
             # Generate a random filename
-            random_id = "".join(
-                random.choices("abcdefghijklmnopqrstuvwxyz0123456789", k=8)
-            )
-            image_filename = f"{prefix}_{random_id}_{i + 1}.png"
+            random_id = ''.join(random.choices('abcdefghijklmnopqrstuvwxyz0123456789', k=8))
+            image_filename = f'{prefix}_{random_id}_{i + 1}.png'
 
         # Decode the base64 image data
         image_data = base64.b64decode(base64_image_data)
 
         # Save the image
         image_path = os.path.join(output_dir, image_filename)
-        with open(image_path, "wb") as file:
+        with open(image_path, 'wb') as file:
             file.write(image_data)
         # Convert to absolute path
         abs_image_path = os.path.abspath(image_path)
         saved_paths.append(abs_image_path)
 
-    return {"paths": saved_paths}
+    return {'paths': saved_paths}
 
 
 async def invoke_nova_canvas(
@@ -112,24 +110,22 @@ async def invoke_nova_canvas(
     Raises:
         Exception: If the API call fails.
     """
-    logger.debug("Invoking Nova Canvas API")
+    logger.debug('Invoking Nova Canvas API')
 
     # Convert the request payload to JSON
     request = json.dumps(request_model_dict)
 
     try:
         # Invoke the model
-        logger.info(f"Sending request to Nova Canvas model: {NOVA_CANVAS_MODEL_ID}")
-        response = bedrock_runtime_client.invoke_model(
-            modelId=NOVA_CANVAS_MODEL_ID, body=request
-        )
+        logger.info(f'Sending request to Nova Canvas model: {NOVA_CANVAS_MODEL_ID}')
+        response = bedrock_runtime_client.invoke_model(modelId=NOVA_CANVAS_MODEL_ID, body=request)
 
         # Decode the response body
-        result = json.loads(response["body"].read())
-        logger.info("Nova Canvas API call successful")
+        result = json.loads(response['body'].read())
+        logger.info('Nova Canvas API call successful')
         return result
     except Exception as e:
-        logger.error(f"Nova Canvas API call failed: {str(e)}")
+        logger.error(f'Nova Canvas API call failed: {str(e)}')
         raise
 
 
@@ -169,22 +165,18 @@ async def generate_image_with_text(
         ImageGenerationResponse: An object containing the paths to the generated images,
         PIL Image objects, and status information.
     """
-    logger.debug(
-        f"Generating text-to-image with prompt: '{prompt[:30]}...' ({width}x{height})"
-    )
+    logger.debug(f"Generating text-to-image with prompt: '{prompt[:30]}...' ({width}x{height})")
 
     try:
         # Validate input parameters using Pydantic
         try:
-            logger.debug("Validating parameters and creating request model")
+            logger.debug('Validating parameters and creating request model')
 
             # Create image generation config
             config = ImageGenerationConfig(
                 width=width,
                 height=height,
-                quality=Quality.STANDARD
-                if quality == DEFAULT_QUALITY
-                else Quality.PREMIUM,
+                quality=Quality.STANDARD if quality == DEFAULT_QUALITY else Quality.PREMIUM,
                 cfgScale=cfg_scale,
                 seed=seed if seed is not None else random.randint(0, 858993459),
                 numberOfImages=number_of_images,
@@ -193,9 +185,7 @@ async def generate_image_with_text(
             # Create text-to-image params
             # The Nova Canvas API doesn't accept null for negativeText
             if negative_prompt is not None:
-                text_params = TextToImageParams(
-                    text=prompt, negativeText=negative_prompt
-                )
+                text_params = TextToImageParams(text=prompt, negativeText=negative_prompt)
             else:
                 text_params = TextToImageParams(text=prompt)
 
@@ -206,13 +196,13 @@ async def generate_image_with_text(
 
             # Convert model to dictionary
             request_model_dict = request_model.to_api_dict()
-            logger.info("Request validation successful")
+            logger.info('Request validation successful')
 
         except Exception as e:
-            logger.error(f"Parameter validation failed: {str(e)}")
+            logger.error(f'Parameter validation failed: {str(e)}')
             return ImageGenerationResponse(
-                status="error",
-                message=f"Validation error: {str(e)}",
+                status='error',
+                message=f'Validation error: {str(e)}',
                 paths=[],
                 prompt=prompt,
                 negative_prompt=negative_prompt,
@@ -220,36 +210,34 @@ async def generate_image_with_text(
 
         try:
             # Invoke the Nova Canvas API
-            logger.debug("Sending request to Nova Canvas API")
-            model_response = await invoke_nova_canvas(
-                request_model_dict, bedrock_runtime_client
-            )
+            logger.debug('Sending request to Nova Canvas API')
+            model_response = await invoke_nova_canvas(request_model_dict, bedrock_runtime_client)
 
             # Extract the image data
-            base64_images = model_response["images"]
-            logger.info(f"Received {len(base64_images)} images from Nova Canvas API")
+            base64_images = model_response['images']
+            logger.info(f'Received {len(base64_images)} images from Nova Canvas API')
 
             # Save the generated images
             result = save_generated_images(
                 base64_images,
                 filename,
                 number_of_images,
-                prefix="nova_canvas",
+                prefix='nova_canvas',
                 workspace_dir=workspace_dir,
             )
 
             logger.info(f'Successfully generated {len(result["paths"])} image(s)')
             return ImageGenerationResponse(
-                status="success",
+                status='success',
                 message=f'Generated {len(result["paths"])} image(s)',
-                paths=result["paths"],
+                paths=result['paths'],
                 prompt=prompt,
                 negative_prompt=negative_prompt,
             )
         except Exception as e:
-            logger.error(f"Image generation failed: {str(e)}")
+            logger.error(f'Image generation failed: {str(e)}')
             return ImageGenerationResponse(
-                status="error",
+                status='error',
                 message=str(e),
                 paths=[],
                 prompt=prompt,
@@ -257,9 +245,9 @@ async def generate_image_with_text(
             )
 
     except Exception as e:
-        logger.error(f"Unexpected error in generate_image_with_text: {str(e)}")
+        logger.error(f'Unexpected error in generate_image_with_text: {str(e)}')
         return ImageGenerationResponse(
-            status="error",
+            status='error',
             message=str(e),
             paths=[],
             prompt=prompt,
@@ -312,17 +300,13 @@ async def generate_image_with_colors(
     try:
         # Validate input parameters using Pydantic
         try:
-            logger.debug(
-                "Validating parameters and creating color-guided request model"
-            )
+            logger.debug('Validating parameters and creating color-guided request model')
 
             # Create image generation config
             config = ImageGenerationConfig(
                 width=width,
                 height=height,
-                quality=Quality.STANDARD
-                if quality == DEFAULT_QUALITY
-                else Quality.PREMIUM,
+                quality=Quality.STANDARD if quality == DEFAULT_QUALITY else Quality.PREMIUM,
                 cfgScale=cfg_scale,
                 seed=seed if seed is not None else random.randint(0, 858993459),
                 numberOfImages=number_of_images,
@@ -349,13 +333,13 @@ async def generate_image_with_colors(
 
             # Convert model to dictionary
             request_model_dict = request_model.to_api_dict()
-            logger.info("Color-guided request validation successful")
+            logger.info('Color-guided request validation successful')
 
         except Exception as e:
-            logger.error(f"Color-guided parameter validation failed: {str(e)}")
+            logger.error(f'Color-guided parameter validation failed: {str(e)}')
             return ImageGenerationResponse(
-                status="error",
-                message=f"Validation error: {str(e)}",
+                status='error',
+                message=f'Validation error: {str(e)}',
                 paths=[],
                 prompt=prompt,
                 negative_prompt=negative_prompt,
@@ -364,39 +348,35 @@ async def generate_image_with_colors(
 
         try:
             # Invoke the Nova Canvas API
-            logger.debug("Sending color-guided request to Nova Canvas API")
-            model_response = await invoke_nova_canvas(
-                request_model_dict, bedrock_runtime_client
-            )
+            logger.debug('Sending color-guided request to Nova Canvas API')
+            model_response = await invoke_nova_canvas(request_model_dict, bedrock_runtime_client)
 
             # Extract the image data
-            base64_images = model_response["images"]
-            logger.info(f"Received {len(base64_images)} images from Nova Canvas API")
+            base64_images = model_response['images']
+            logger.info(f'Received {len(base64_images)} images from Nova Canvas API')
 
             # Save the generated images
             result = save_generated_images(
                 base64_images,
                 filename,
                 number_of_images,
-                prefix="nova_canvas_color",
+                prefix='nova_canvas_color',
                 workspace_dir=workspace_dir,
             )
 
-            logger.info(
-                f'Successfully generated {len(result["paths"])} color-guided image(s)'
-            )
+            logger.info(f'Successfully generated {len(result["paths"])} color-guided image(s)')
             return ImageGenerationResponse(
-                status="success",
+                status='success',
                 message=f'Generated {len(result["paths"])} image(s)',
-                paths=result["paths"],
+                paths=result['paths'],
                 prompt=prompt,
                 negative_prompt=negative_prompt,
                 colors=colors,
             )
         except Exception as e:
-            logger.error(f"Color-guided image generation failed: {str(e)}")
+            logger.error(f'Color-guided image generation failed: {str(e)}')
             return ImageGenerationResponse(
-                status="error",
+                status='error',
                 message=str(e),
                 paths=[],
                 prompt=prompt,
@@ -405,9 +385,9 @@ async def generate_image_with_colors(
             )
 
     except Exception as e:
-        logger.error(f"Unexpected error in generate_image_with_colors: {str(e)}")
+        logger.error(f'Unexpected error in generate_image_with_colors: {str(e)}')
         return ImageGenerationResponse(
-            status="error",
+            status='error',
             message=str(e),
             paths=[],
             prompt=prompt,