Generate Stunning Images with the prunaai/sdxl-turbo Cognitive Actions

22 Apr 2025
Generate Stunning Images with the prunaai/sdxl-turbo Cognitive Actions

In the realm of artificial intelligence, the ability to create stunning visuals from textual descriptions has become a groundbreaking tool for developers. The prunaai/sdxl-turbo API provides a powerful Cognitive Action that allows you to generate high-quality images based on textual prompts. This article will guide you through integrating this action into your applications, unlocking creative possibilities.

Prerequisites

To get started with the Cognitive Actions in the prunaai/sdxl-turbo spec, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic understanding of JSON and interacting with APIs.
  • Access to a suitable development environment for making HTTP requests.

Authentication is typically handled by passing your API key in the request headers. This ensures that only authorized users can access the image generation capabilities.

Cognitive Actions Overview

Generate Image with Text Prompt

The Generate Image with Text Prompt action allows you to create one or more high-quality images from a textual description. By utilizing the SDXL-Turbo model, you can customize various parameters such as image size, number of images, and inference steps to achieve your desired output.

Input

The input for this action is structured in a JSON format, requiring the following fields:

  • prompt (required): A textual description to generate an image from.
  • seed (optional): An integer seed value for randomization (default is 42).
  • imageWidth (optional): The width of the generated image in pixels (default is 1024).
  • imageHeight (optional): The height of the generated image in pixels (default is 1024).
  • guidanceScale (optional): A floating-point number that determines the guidance scale for image generation (default is 7.5).
  • numberOfImages (optional): The total number of images to generate (default is 1).
  • numberOfInferenceSteps (optional): The number of inference steps for the image generation process (default is 50).

Example Input:

{
  "seed": 42,
  "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
  "imageWidth": 768,
  "imageHeight": 768,
  "guidanceScale": 7.5,
  "numberOfImages": 1,
  "numberOfInferenceSteps": 25
}

Output

The output of this action typically returns a URL link to the generated image. For example:

Example Output:

https://assets.cognitiveactions.com/invocations/5a08d95d-3194-4a26-9d49-a4de1fda3bff/aa3f188a-7be7-4751-832d-a0a0208ff94f.png

This URL points to the generated image that you can use in your applications.

Conceptual Usage Example (Python)

Here’s how you can call the Generate Image with Text Prompt 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 = "9a021523-16e4-4503-b420-ffeaa35bef6c" # Action ID for Generate Image with Text Prompt

# Construct the input payload based on the action's requirements
payload = {
    "seed": 42,
    "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
    "imageWidth": 768,
    "imageHeight": 768,
    "guidanceScale": 7.5,
    "numberOfImages": 1,
    "numberOfInferenceSteps": 25
}

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 Python code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the specific action you are invoking, and the payload is the JSON structure that specifies the image generation parameters. The response will contain the URL of the generated image.

Conclusion

The prunaai/sdxl-turbo Cognitive Actions empower developers to create stunning images from textual descriptions effortlessly. By leveraging the capabilities of the Generate Image with Text Prompt action, you can enhance your applications with creative visuals. Consider experimenting with various prompts and parameters to discover the full potential of this powerful tool. Happy coding!

← Back to All Articles