Generate Stunning Images with Costanza Cognitive Actions

23 Apr 2025
Generate Stunning Images with Costanza Cognitive Actions

In the world of artificial intelligence and machine learning, image generation has taken a front seat, allowing developers to create breathtaking visuals using advanced techniques. The Costanza Cognitive Actions provide a robust API for generating high-quality images via inpainting and customization options. With features like adjustable size, aspect ratio, and varied processing models, these pre-built actions simplify the integration of image generation capabilities into your applications.

Prerequisites

To get started with Costanza Cognitive Actions, you'll need the following:

  • API Key: Register on the Cognitive Actions platform to obtain your API key.
  • Environment Setup: Make sure your development environment can handle HTTP requests, such as using the requests library in Python.

For authentication, you will typically pass your API key in the headers of the requests you make to the Cognitive Actions endpoint.

Cognitive Actions Overview

Generate Image with Inpainting and Customization

Description: Generate high-quality images using image-to-image and inpainting techniques with customizable options for size, aspect ratio, and LoRA intensity. Choose between models optimized for speed or step accuracy for diverse styles and concepts.

Category: Image Generation

Input

The input schema for this action is a composite request object that requires a prompt and allows various optional parameters. Below are the key input fields:

  • prompt (required): Text prompt to guide the generation of the image.
  • image (optional): URI of the input image for inpainting.
  • mask (optional): URI of the image mask for inpainting.
  • width and height (optional): Specify the dimensions of the output image.
  • imageFormat (optional): Format of the output image (default: webp).
  • outputCount (optional): How many images to generate (default: 1, max: 4).
  • imageQuality (optional): Quality of the saved images (default: 80).
  • speedOptimized (optional): Enable faster predictions (default: false).
  • mainLoraIntensity and additionalLoraIntensity (optional): Control the intensity of LoRA applications.

Example Input:

{
  "prompt": "costanza  A six-month-old baby sitting on a messy couch in a colorful living room, holding a spoon in front of an empty Gerber jar, with a frustrated expression as if someone just stole his food.\n\n",
  "imageFormat": "jpg",
  "outputCount": 1,
  "imageQuality": 80,
  "speedOptimized": false,
  "imageResolution": "1",
  "processingModel": "dev",
  "imageAspectRatio": "16:9",
  "mainLoraIntensity": 1,
  "inferenceStepCount": 28,
  "promptInfluenceLevel": 0.8,
  "additionalLoraIntensity": 1,
  "diffusionGuidanceIntensity": 3
}

Output

The action returns a URL to the generated image. The output structure typically looks like this:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/8feb4c05-a1ed-4725-9aa4-cde1e13c5aff/702d5258-4822-4921-8a92-6303569f7abd.jpg"
]

Conceptual Usage Example (Python)

Here’s how you might call the Costanza Cognitive Actions to generate an image 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 = "565dec4f-9da0-4610-8b90-8b71a1c87f51"  # Action ID for Generate Image with Inpainting and Customization

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "costanza  A six-month-old baby sitting on a messy couch in a colorful living room, holding a spoon in front of an empty Gerber jar, with a frustrated expression as if someone just stole his food.\n\n",
    "imageFormat": "jpg",
    "outputCount": 1,
    "imageQuality": 80,
    "speedOptimized": False,
    "imageResolution": "1",
    "processingModel": "dev",
    "imageAspectRatio": "16:9",
    "mainLoraIntensity": 1,
    "inferenceStepCount": 28,
    "promptInfluenceLevel": 0.8,
    "additionalLoraIntensity": 1,
    "diffusionGuidanceIntensity": 3
}

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. The payload variable is structured based on the input requirements for the image generation action. The endpoint and request structure are illustrative and may change as per actual API specifications.

Conclusion

The Costanza Cognitive Actions offer a powerful way to integrate image generation capabilities into your applications effortlessly. By leveraging the flexibility of customizable prompts and settings, developers can create a wide array of unique images tailored to their needs. Explore these actions further to unlock the full potential of AI-driven image creation in your projects!

← Back to All Articles