Unleash Your Creativity: Integrating Image Generation with guillaumesimon/radostina2 Cognitive Actions

23 Apr 2025
Unleash Your Creativity: Integrating Image Generation with guillaumesimon/radostina2 Cognitive Actions

In the realm of digital creativity, the ability to generate custom images can transform the way applications interact with users. The guillaumesimon/radostina2 specification provides developers with powerful Cognitive Actions designed for advanced image generation. With capabilities such as inpainting and transformation, these actions allow for enhanced control over image quality, style, and content, making it easier than ever to bring imaginative concepts to life.

Prerequisites

Before diving into the integration of Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of JSON format, as you'll be constructing JSON payloads for the API calls.
  • Familiarity with making HTTP requests, particularly using libraries like requests in Python.

Authentication typically involves passing your API key in the headers of your requests.

Cognitive Actions Overview

Generate Custom Image

The Generate Custom Image action allows you to create custom images by leveraging advanced inpainting and image transformation capabilities. This action is invaluable for applications that require dynamic image generation based on user inputs or predefined prompts.

Input

The action requires a structured input following the schema outlined below. Here’s an example of the input structure:

{
  "width": 1024,
  "height": 1024,
  "prompt": "black and white pencil illustration of a child surfing a wave made of books, in the style of benji davies",
  "refine": "no_refiner",
  "loraScale": 0.78,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "excludedPrompt": "water",
  "promptStrength": 0.8,
  "numberOfOutputs": 2,
  "highNoiseFraction": 0.8,
  "numInferenceSteps": 50
}

Input Fields:

  • width (integer): The width of the output image in pixels (default: 1024).
  • height (integer): The height of the output image in pixels (default: 1024).
  • prompt (string): A text prompt guiding the image generation (default: "An astronaut riding a rainbow unicorn").
  • refine (string): Specifies the style of refinement (default: "no_refiner").
  • loraScale (number): Scale factor for LoRA models (default: 0.6, range: 0-1).
  • scheduler (string): Algorithm for scheduling denoising steps (default: "K_EULER").
  • guidanceScale (number): Intensity of guidance during generation (default: 7.5, range: 1-50).
  • applyWatermark (boolean): Whether to apply a watermark (default: true).
  • excludedPrompt (string): Elements to exclude from generation (default: "").
  • promptStrength (number): Strength of the prompt (default: 0.8, range: 0-1).
  • numberOfOutputs (integer): Number of images to generate (default: 1, max: 4).
  • highNoiseFraction (number): Fraction of noise for refinement (default: 0.8).
  • numInferenceSteps (integer): Total number of denoising steps (default: 50, max: 500).

Output

Upon successful execution, the action returns an array of URLs pointing to the generated images. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/c7c964d5-7fd7-4b6c-9ee9-953a475c6997/3d62ec91-aac5-4756-a70c-ed392d74d0f4.png",
  "https://assets.cognitiveactions.com/invocations/c7c964d5-7fd7-4b6c-9ee9-953a475c6997/b08b0677-18f7-4ec8-be3b-b07d7df200f8.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how to call the Generate Custom Image action using Python:

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 = "5c749c12-ae0a-47a7-87ca-a716ee00571e"  # Action ID for Generate Custom Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "black and white pencil illustration of a child surfing a wave made of books, in the style of benji davies",
    "refine": "no_refiner",
    "loraScale": 0.78,
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "excludedPrompt": "water",
    "promptStrength": 0.8,
    "numberOfOutputs": 2,
    "highNoiseFraction": 0.8,
    "numInferenceSteps": 50
}

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 the placeholders with your actual API key and endpoint. The input payload is structured based on the requirements of the Generate Custom Image action, allowing you to easily generate images based on your specifications.

Conclusion

The guillaumesimon/radostina2 Cognitive Actions open up a world of possibilities for image generation in your applications. By understanding how to utilize the Generate Custom Image action, you can create unique images tailored to user input or specific design needs. Consider exploring additional use cases such as integrating this functionality into creative projects, design tools, or social media applications. Happy coding!

← Back to All Articles