Generate Stunning Images with aekeel/audie Cognitive Actions

21 Apr 2025
Generate Stunning Images with aekeel/audie Cognitive Actions

In the world of AI-driven creativity, the aekeel/audie API provides powerful Cognitive Actions that enable developers to generate images with remarkable customization options. These pre-built actions simplify the integration of image generation capabilities into applications, allowing for rich, unique content creation. By leveraging these actions, developers can easily create images tailored to specific parameters, enhancing user experiences across various domains.

Prerequisites

To get started with the aekeel/audie Cognitive Actions, you'll need to ensure you have access to the Cognitive Actions platform. This typically involves obtaining an API key from the service provider. Authentication usually works by passing this API key in the request headers, authorizing you to make calls to the image generation endpoints.

Cognitive Actions Overview

Generate Image with Custom Parameters

The Generate Image with Custom Parameters action allows users to create images by specifying a variety of customizable parameters, including size, prompt strength, and guidance scale. This action can utilize image-to-image transformations or inpainting modes, supporting models optimized for either speed or quality.

Input: The input for this action requires the following fields, with additional optional parameters to fine-tune the image generation:

{
  "model": "dev",
  "goFast": false,
  "prompt": "audie with long spiral curled auburn hair, in light blue long frilly maternity gown, with sheer fabric on belly, pregnant",
  "loraScale": 1,
  "megapixels": "1",
  "numOutputs": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3,
  "outputQuality": 80,
  "promptStrength": 0.8,
  "numInferenceSteps": 28,
  "additionalLoraScale": 1
}
  • Required Field:
    • prompt: A detailed description of the image to be generated.
  • Optional Fields:
    • model: Specifies the inference model (e.g., "dev" or "schnell").
    • goFast: Enables faster predictions with a model optimized for speed.
    • loraScale: Determines the application strength of the main LoRA.
    • numOutputs: Specifies how many images to generate.
    • aspectRatio: Defines the aspect ratio for the generated image.
    • outputFormat: Specifies the file format for the images (e.g., "webp", "jpg", "png").
    • guidanceScale: Influences the image generation process.
    • outputQuality: Sets the quality level for output images.
    • promptStrength: Defines how strongly the prompt influences the image.
    • And several other parameters for advanced configurations.

Output: The action typically returns a URL to the generated image, as shown below:

[
  "https://assets.cognitiveactions.com/invocations/67ff9e4c-eca2-4649-911c-08f6e4af33af/e9300a44-3e05-4701-814e-f7643c95a450.webp"
]

This URL points to the generated image, allowing you to easily access and display it within your application.

Conceptual Usage Example (Python): Here's a conceptual Python code snippet demonstrating how to call this action using a hypothetical Cognitive Actions API endpoint:

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 = "ff378009-0bea-4b05-a81d-3094b297bb56"  # Action ID for Generate Image with Custom Parameters

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "audie with long spiral curled auburn hair, in light blue long frilly maternity gown, with sheer fabric on belly, pregnant",
    "loraScale": 1,
    "megapixels": "1",
    "numOutputs": 1,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3,
    "outputQuality": 80,
    "promptStrength": 0.8,
    "numInferenceSteps": 28,
    "additionalLoraScale": 1
}

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 example, the action_id is set to the ID of the action for generating images, and the payload is structured according to the required input schema. The headers include the API key for authorization.

Conclusion

The aekeel/audie Cognitive Actions empower developers to seamlessly integrate advanced image generation capabilities into their applications. With customizable parameters, these actions open up a world of creative possibilities, enabling the generation of unique images tailored to specific user needs. As you explore these capabilities, consider experimenting with different configurations to achieve the desired artistic outcomes in your projects. Happy coding!

← Back to All Articles