Transforming Images with StyleMC: A Developer's Guide to Cognitive Actions

22 Apr 2025
Transforming Images with StyleMC: A Developer's Guide to Cognitive Actions

In the world of AI and computer vision, generating and editing images has become remarkably accessible with the advent of powerful models like StyleMC. The adirik/stylemc Cognitive Actions provide developers with the ability to leverage text-guided image generation and manipulation, allowing for tailored facial style transformations with high precision and speed. This guide will walk you through how to integrate the Generate and Edit Images with StyleMC action into your applications, enhancing your image processing capabilities.

Prerequisites

Before diving into the integration, ensure you have the following setup:

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with JSON and Python programming.
  • Basic knowledge of making HTTP requests.

To authenticate, you will typically pass your API key in the headers of your requests, allowing you to securely access the Cognitive Actions.

Cognitive Actions Overview

Generate and Edit Images with StyleMC

The Generate and Edit Images with StyleMC action enables rapid image generation and manipulation based on text prompts. This action is particularly useful for applications that require customized facial transformations, allowing you to create images that fit specific descriptions.

Input

The input for this action requires a JSON object that includes the following fields:

  • image (required): The URI of the input face image.
  • prompt (optional): A predefined prompt describing the desired output. You can choose from several predefined options or use a custom prompt.
  • changeAlpha (optional): An integer that defines the strength coefficient for applying the style direction, ranging from -50 to 50.
  • customPrompt (optional): A string to enter a more detailed, custom prompt, which will override the predefined prompt.
  • identityLossCoefficient (optional): A number that determines how much identity preservation is required, with a range from 0 to 5.

Example Input:

{
  "image": "https://replicate.delivery/pbxt/KX8JZ1ZTBj6oSh78QKOExLXcDGWV4eB5Z3z9gnFCmMMJxynH/stylemc_sample.jpg",
  "prompt": "a photo of a happy face"
}

Output

Upon successful execution, the action returns a URI that points to the generated image based on the input parameters.

Example Output:

https://assets.cognitiveactions.com/invocations/cd20fef7-3461-4908-a83e-fab70587dafd/859b0500-0ab6-4ee5-88d6-93fb5d207c89.jpg

Conceptual Usage Example (Python)

Here's a conceptual example of how you might call the Cognitive Actions execution endpoint to generate and edit images using StyleMC:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "e25e1499-9dca-4e8a-b5a5-92735c8efdb2" # Action ID for Generate and Edit Images with StyleMC

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/KX8JZ1ZTBj6oSh78QKOExLXcDGWV4eB5Z3z9gnFCmMMJxynH/stylemc_sample.jpg",
    "prompt": "a photo of a happy face"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is constructed according to the required input schema, and you’ll find the action ID and input payload clearly defined.

Conclusion

The Generate and Edit Images with StyleMC action empowers developers to create and manipulate images efficiently, making it a valuable tool for applications in various domains such as entertainment, design, and social media. By understanding the input requirements and how to structure your requests, you can easily integrate this functionality into your applications. Explore the possibilities offered by StyleMC and enhance your creative projects today!

← Back to All Articles