Enhance Your Apps with Image Generation Using Lunaon2023 Cognitive Actions

22 Apr 2025
Enhance Your Apps with Image Generation Using Lunaon2023 Cognitive Actions

In the rapidly evolving landscape of artificial intelligence, the ability to generate customized images from textual prompts opens up new creative avenues for developers. The Lunaon2023/repro31 Cognitive Actions provide a seamless way to produce refined images tailored to specific needs. By leveraging these pre-built actions, developers can enhance their applications with sophisticated image generation capabilities, allowing for unique visual content creation that meets a wide range of user demands.

Prerequisites

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

  • API Key: You will need an API key to authenticate your requests to the Cognitive Actions platform.
  • Basic Understanding of JSON: Familiarity with JSON structure is essential for constructing input payloads and processing outputs.

To authenticate your requests conceptually, include your API key in the request headers as follows:

Authorization: Bearer YOUR_COGNITIVE_ACTIONS_API_KEY
Content-Type: application/json

Cognitive Actions Overview

Generate Refined Image

The Generate Refined Image action is designed to create a customized image based on your textual prompts. It allows you to specify various parameters such as resolution, noise control, and refinement styles, ensuring high-quality and tailored outputs that meet your needs.

Input

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

  • seed (integer, optional): Initializes the random number generator. Leave blank for a random seed.
  • width (integer, default: 1024): The width of the output image in pixels.
  • height (integer, default: 1024): The height of the output image in pixels.
  • prompt (string, required): A textual input describing the desired output.
  • refine (string, default: "expert_ensemble_refiner"): Specifies the refinement style for image generation. Options include:
    • no_refiner
    • base_image_refiner
    • expert_ensemble_refiner
  • scheduler (string, default: "DDIM"): Selects the type of scheduler for the denoising process. Options include:
    • DDIM
    • DPMSolverMultistep
    • HeunDiscrete
    • K_EULER_ANCESTRAL
    • K_EULER
    • PNDM
  • refineSteps (integer, optional): For base_image_refiner, specifies the number of refinement steps.
  • guidanceScale (number, default: 7.5, range: 1-50): A scaling factor for classifier-free guidance.
  • negativePrompt (string, optional): Specifies undesired content in the output.
  • highNoiseFraction (number, default: 0.8, range: 0-1): For expert_ensemble_refiner, specifies the fraction of noise applied.
  • numInferenceSteps (integer, default: 50, range: 1-500): The total number of steps for the denoising process.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "1girl,mahogany hair,short hair, twin braids hair, asymmetrical bangs bangs,,Create a bohemian-style image, with eclectic patterns, earthy colors, and a sense of free-spiritedness and individuality.",
  "refine": "expert_ensemble_refiner",
  "scheduler": "DDIM",
  "guidanceScale": 7.5,
  "negativePrompt": "",
  "highNoiseFraction": 0.8,
  "numInferenceSteps": 50
}

Output

Upon successful execution, the action typically returns a URL pointing to the generated image. For example:

https://assets.cognitiveactions.com/invocations/e83a3ade-2d1b-4822-9d87-81497f042193/4470d403-99ff-441c-a984-de5bb0aecae0.png

Conceptual Usage Example (Python)

Here’s how you might invoke the Generate Refined 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 = "8bb06e65-65f2-4cf6-80e9-b17d2f9bceca" # Action ID for Generate Refined Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "1girl,mahogany hair,short hair, twin braids hair, asymmetrical bangs bangs,,Create a bohemian-style image, with eclectic patterns, earthy colors, and a sense of free-spiritedness and individuality.",
    "refine": "expert_ensemble_refiner",
    "scheduler": "DDIM",
    "guidanceScale": 7.5,
    "negativePrompt": "",
    "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, be sure to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id is set to the ID for the Generate Refined Image action. The payload is structured according to the action's input requirements.

Conclusion

Integrating the Generate Refined Image action into your applications can empower you to create unique and personalized visual content effortlessly. By utilizing the flexible input parameters, you can tailor the outputs to suit various creative needs. Consider experimenting with different prompts and settings to discover the full potential of this powerful cognitive action. As you explore these capabilities, think about how they can enhance user engagement and enrich the overall experience of your applications.

← Back to All Articles