Create Stunning Images with the siamakf/petpatrol-joyi Cognitive Actions

24 Apr 2025
Create Stunning Images with the siamakf/petpatrol-joyi Cognitive Actions

In the world of artificial intelligence, the ability to generate high-quality images from text prompts has opened up new avenues for creativity and innovation. The siamakf/petpatrol-joyi spec offers developers a powerful Cognitive Action for generating realistic images using advanced techniques like inpainting and image-to-image processing. This article will walk you through how to harness these capabilities in your applications, enabling you to create visually engaging content with ease.

Prerequisites

Before you dive into using 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.
  • Environment Setup: Make sure you have a development environment ready for making HTTP requests. Python and the requests library are recommended for ease of use.

Authentication typically involves passing your API key in the request headers to authorize access to the Cognitive Actions.

Cognitive Actions Overview

Generate High-Quality Predictive Images

This action generates high-quality, realistic images based on a provided text prompt. It utilizes advanced inpainting and image-to-image techniques, allowing for various model customizations for optimal performance.

Input

The input for this action follows the schema defined below:

{
  "prompt": "string (required)",
  "model": "string (optional, default: dev)",
  "width": "integer (optional)",
  "height": "integer (optional)",
  "aspectRatio": "string (optional, default: 1:1)",
  "outputCount": "integer (optional, default: 1)",
  "denoiseSteps": "integer (optional, default: 28)",
  "outputFormat": "string (optional, default: webp)",
  "guidanceScale": "number (optional, default: 3)",
  "loraIntensity": "number (optional, default: 1)",
  "outputQuality": "integer (optional, default: 80)",
  "additionalLora": "string (optional)",
  "extraLoraScale": "number (optional, default: 1)"
}
Example Input

Here’s an example of how to structure the JSON payload for this action:

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "Extremely aesthetically pleasing photo of a HAPPY golden retriever chasing a squirrel. Depict a well lit, beautiful, sunny day with clear blue skies. The atmosphere should be lively and inviting. Show a big beautiful red barn in the scene. Emphasize the beautiful light of day. Display the dog in extremely high fidelity. Use extreme level of depth of field to separate dog from the background. Keep details of dog realistic. DO NOT display genitals of dog. Keep dog's facial expression very happy. Render 4 limbs maximum. surrounded by illustrations of cheese, bacon, dog biscuits, sparkles, rock and roll",
  "aspectRatio": "1:1",
  "outputCount": 4,
  "denoiseSteps": 28,
  "outputFormat": "png",
  "guidanceScale": 3.5,
  "loraIntensity": 1,
  "outputQuality": 100,
  "additionalLora": "davisbrown/flux-half-illustration",
  "extraLoraScale": 0.8
}

Output

Upon successful execution, this action returns an array of image URLs that correspond to the generated images. Here’s an example of the output you might receive:

[
  "https://assets.cognitiveactions.com/invocations/bc34d97f-6ad3-456b-b0df-7780f29e202d/50d49394-c62f-4639-8afd-162ad5a2e01b.png",
  "https://assets.cognitiveactions.com/invocations/bc34d97f-6ad3-456b-b0df-7780f29e202d/22827bc8-4739-47ed-9854-d4e1ce028a29.png",
  "https://assets.cognitiveactions.com/invocations/bc34d97f-6ad3-456b-b0df-7780f29e202d/6fbd4f34-3a32-422e-b438-647cd7d547eb.png",
  "https://assets.cognitiveactions.com/invocations/bc34d97f-6ad3-456b-b0df-7780f29e202d/20b0a28d-b14c-412c-8f6b-04cb74523370.png"
]

Conceptual Usage Example (Python)

Here’s how you might call this action in a Python application:

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 = "90ef6806-ba46-4e96-a72b-ec2777791410"  # Action ID for Generate High-Quality Predictive Images

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "Extremely aesthetically pleasing photo of a HAPPY golden retriever chasing a squirrel. Depict a well lit, beautiful, sunny day with clear blue skies...",
    "aspectRatio": "1:1",
    "outputCount": 4,
    "denoiseSteps": 28,
    "outputFormat": "png",
    "guidanceScale": 3.5,
    "loraIntensity": 1,
    "outputQuality": 100,
    "additionalLora": "davisbrown/flux-half-illustration",
    "extraLoraScale": 0.8
}

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 the YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID corresponds to the image generation action, and the payload is structured as described above.

Conclusion

The siamakf/petpatrol-joyi Cognitive Actions provide a highly versatile tool for developers looking to enhance their applications with advanced image generation capabilities. By leveraging these actions, you can create rich visual content tailored to your specifications. Whether you're building an app for creative storytelling, marketing, or any other purpose, these tools can significantly elevate your offerings. Start experimenting with these actions today and unlock new possibilities!

← Back to All Articles