Unlock Creative Possibilities with Image Generation using NSDXL Cognitive Actions

21 Apr 2025
Unlock Creative Possibilities with Image Generation using NSDXL Cognitive Actions

In today's digital landscape, the ability to generate high-quality images on demand can greatly enhance applications in various fields, from entertainment to marketing. The NSDXL Cognitive Actions provide developers with powerful tools for image generation, leveraging advanced AI capabilities. This article will delve into the Generate Image with NSDXL action, explaining how to utilize its features to create stunning visuals tailored to your needs.

Prerequisites

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

  • An API key for the Cognitive Actions platform. This key will authenticate your requests.
  • Basic knowledge of making HTTP requests and handling JSON payloads.

For authentication, you will generally include your API key in the request headers, allowing you to securely access the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with NSDXL

The Generate Image with NSDXL action allows you to generate images using an AI model that supports img2img and inpaint modes. This action is designed to empower developers to create customizable images by defining areas to preserve or alter, managing output dimensions, and applying specific guidance through text prompts. It also offers options for watermarking and safety checks, ensuring quality and flexibility.

Input

The input for this action is structured as a JSON object, including the following fields:

  • mask (optional): URI for the input mask in inpainting mode.
  • seed (optional): Random seed for generation (leave blank for random).
  • image (optional): URI for the input image used in img2img or inpainting mode.
  • width (default: 1024): Width of the output image in pixels.
  • height (default: 1024): Height of the output image in pixels.
  • prompt (default: "An astronaut riding a rainbow unicorn"): Text prompt for guiding image generation.
  • loraScale (default: 0.6): Scale factor for applying LoRA to the model.
  • outputCount (default: 1): Number of images to generate (1-4).
  • refineStyle (default: "no_refiner"): Style of refinement to apply.
  • scheduleType (default: "K_EULER"): Denoising scheduling strategy.
  • guidanceScale (default: 7.5): Influence of the prompt on the output.
  • promptStrength (default: 0.8): Degree of prompt influence in img2img or inpainting.
  • watermarkEnabled (default: true): Enable watermarking for generated images.
  • inferenceStepsCount (default: 50): Total number of denoising steps.
  • negativeInputPrompt (optional): Aspects to avoid in the generated image.
  • safetyCheckerDisabled (default: false): Option to disable the safety checker.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "astronaut riding a horse, NSDXL",
  "loraScale": 0.8,
  "outputCount": 1,
  "refineStyle": "no_refiner",
  "scheduleType": "KarrasDPM",
  "guidanceScale": 7.5,
  "promptStrength": 0.8,
  "watermarkEnabled": false,
  "highNoiseFraction": 0.8,
  "inferenceStepsCount": 50,
  "negativeInputPrompt": ""
}

Output

The action typically returns a JSON array containing the URLs of the generated images. For example:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/16fd72f5-896d-402c-a099-a7dd4b8d577d/a25d476b-2001-47d6-9891-b969fc8dcb38.png"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image with NSDXL action using Python. This snippet demonstrates constructing the input payload and making the request:

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 = "e3b77c28-6443-44e3-9ca5-ab11417f70ff"  # Action ID for Generate Image with NSDXL

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "astronaut riding a horse, NSDXL",
    "loraScale": 0.8,
    "outputCount": 1,
    "refineStyle": "no_refiner",
    "scheduleType": "KarrasDPM",
    "guidanceScale": 7.5,
    "promptStrength": 0.8,
    "watermarkEnabled": False,
    "highNoiseFraction": 0.8,
    "inferenceStepsCount": 50,
    "negativeInputPrompt": ""
}

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.
  • Set the action_id to the ID of the Generate Image action.
  • The payload is structured according to the input schema, and a request is sent to the hypothetical execution URL.

Conclusion

The Generate Image with NSDXL action opens up a world of creative possibilities for developers. By leveraging its capabilities, you can enhance your applications with bespoke images that are generated based on specific needs and prompts. Explore the various configuration options available to tailor the outputs to your desired specifications. As you integrate these Cognitive Actions into your projects, consider experimenting with different parameters to unlock even more creative potential. Happy coding!

← Back to All Articles