Create Stunning Images with the omarprama/xot-ppl-shrt Cognitive Action

23 Apr 2025
Create Stunning Images with the omarprama/xot-ppl-shrt Cognitive Action

In today's digital landscape, the ability to generate high-quality images programmatically can transform applications across various domains, from marketing to gaming. The omarprama/xot-ppl-shrt specification introduces an advanced Cognitive Action that allows developers to leverage powerful image generation techniques through a simple API. This action enables you to create images using inpainting techniques, providing options for customization and optimization.

Prerequisites

Before you dive into implementing the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Familiarity with making HTTP requests and handling JSON data in your programming environment.

For authentication, you will typically include your API key in the headers of your requests. This allows you to securely access the Cognitive Actions and utilize their capabilities.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action is designed for generating images using advanced inpainting techniques. You can customize various parameters such as image dimensions, model types, and output quality. This action is particularly beneficial for applications that require refined image generation capabilities, whether for artistic creation or enhancing existing images.

Input

The action accepts a structured input defined by the following schema:

{
  "prompt": "string (required)",
  "mask": "string (optional, uri)",
  "seed": "integer (optional)",
  "image": "string (optional, uri)",
  "model": "string (default: 'dev')",
  "width": "integer (optional, min: 256, max: 1440)",
  "height": "integer (optional, min: 256, max: 1440)",
  "fastMode": "boolean (default: false)",
  "aspectRatio": "string (default: '1:1')",
  "loraIntensity": "number (default: 1, min: -1, max: 3)",
  "promptStrength": "number (default: 0.8, min: 0, max: 1)",
  "numberOfOutputs": "integer (default: 1, min: 1, max: 4)",
  "guidanceIntensity": "number (default: 3, min: 0, max: 10)",
  "imageOutputFormat": "string (default: 'webp')",
  "imageOutputQuality": "integer (default: 80, min: 0, max: 100)",
  "numberOfInferenceSteps": "integer (default: 28, min: 1, max: 50)"
}

Here's an example of the JSON payload needed to invoke this action:

{
  "model": "dev",
  "width": 784,
  "height": 784,
  "prompt": "XOT",
  "aspectRatio": "1:1",
  "loraIntensity": 1,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "guidanceIntensity": 3.5,
  "imageOutputFormat": "jpg",
  "imageOutputQuality": 90,
  "numberOfInferenceSteps": 28
}

Output

Upon executing the action, you can expect an output structured like this:

[
  "https://assets.cognitiveactions.com/invocations/77537854-c21c-4bcb-a565-39cad532802c/1a4c2c97-37a2-4150-b583-e1423fa8f8d1.jpg"
]

This indicates that the action successfully generated an image, and the URL provided can be used to access the created image.

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might invoke the Generate Image with Inpainting 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 = "f46562db-e711-472a-ade8-e5ab54113ab1"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "width": 784,
    "height": 784,
    "prompt": "XOT",
    "aspectRatio": "1:1",
    "loraIntensity": 1,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "guidanceIntensity": 3.5,
    "imageOutputFormat": "jpg",
    "imageOutputQuality": 90,
    "numberOfInferenceSteps": 28
}

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, and adjust the endpoint URL as necessary. The action ID and input payload are structured according to the requirements defined previously.

Conclusion

The Generate Image with Inpainting action from the omarprama/xot-ppl-shrt specification offers a robust tool for developers looking to integrate advanced image generation capabilities into their applications. By leveraging this Cognitive Action, you can create stunning visuals tailored to your specifications.

Explore the possibilities and consider how you might implement this action to elevate your applications with dynamic and high-quality image content!

← Back to All Articles