Enhance Your Applications with Image Generation Using go-xoxo/petar-face1 Cognitive Actions

25 Apr 2025
Enhance Your Applications with Image Generation Using go-xoxo/petar-face1 Cognitive Actions

In the evolving landscape of artificial intelligence, image generation has become a captivating frontier. The go-xoxo/petar-face1 Cognitive Actions offer developers a powerful toolkit to create and manipulate images through a simple API interface. This particular set of Cognitive Actions allows for sophisticated image refinements using inpainting techniques, enabling you to generate stunning visuals that can elevate your applications.

Prerequisites

Before diving into the integration of these Cognitive Actions, make sure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of JSON structure, as you will be formatting your input data in this format.
  • Familiarity with Python and the requests library for making HTTP calls.

To authenticate, you will typically pass your API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Inpainted Image

The Generate Inpainted Image action is designed to create an inpainted image based on a specified input image and mask. This action is particularly beneficial for refining images by allowing you to specify certain areas to be preserved or altered. Key features include text prompts, configurable image dimensions, and options for noise handling and watermarking.

Input:

The required and optional fields for this action are as follows:

{
  "mask": "https://example.com/path/to/mask.png",
  "seed": 12345,
  "image": "https://example.com/path/to/image.png",
  "width": 1024,
  "height": 1024,
  "prompt": "a king",
  "refine": "no_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "refineSteps": 10,
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "a bad feature",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}
  • mask (string): URI for the input mask in inpaint mode.
  • image (string): URI for the input image.
  • width (integer): Width of the output image in pixels (defaults to 1024).
  • height (integer): Height of the output image in pixels (defaults to 1024).
  • prompt (string): Text prompt guiding the image generation.
  • refine (string): Method to refine the image generation result.
  • loraScale (number): LoRA additive scaling factor (defaults to 0.6).
  • scheduler (string): Algorithm for denoising (defaults to 'K_EULER').
  • guidanceScale (number): Guidance scale for classifier-free methods (defaults to 7.5).
  • applyWatermark (boolean): Indicates whether a watermark is applied (defaults to true).
  • promptStrength (number): Influence of the prompt in the generation (defaults to 0.8).
  • numberOfOutputs (integer): Specifies the number of images to generate (defaults to 1).
  • highNoiseFraction (number): Fraction of noise to use with the expert ensemble refiner (defaults to 0.8).
  • numberOfInferenceSteps (integer): Count of denoising steps in the generation process (defaults to 50).

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "a king",
  "refine": "no_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}

Output:

The action typically returns a URL pointing to the generated image:

[
  "https://assets.cognitiveactions.com/invocations/1dd58c7b-65f3-4aba-8927-debc7cf12c6b/b4ff3d06-00cf-4f93-ab65-5c9af8bdb43d.png"
]

Conceptual Usage Example (Python):

Here’s how you might call this action in 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 = "fd8a0ba7-bc88-4be8-9004-6bed404ceb03" # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "a king",
    "refine": "no_refiner",
    "loraScale": 0.6,
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "highNoiseFraction": 0.8,
    "numberOfInferenceSteps": 50
}

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 example, you will replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The input payload is structured based on the action’s requirements, and the response will contain the URL to the generated image.

Conclusion

The go-xoxo/petar-face1 Cognitive Actions provide a robust framework for image generation, allowing developers to leverage sophisticated techniques like inpainting with minimal effort. By integrating these actions into your applications, you can create unique and visually engaging content tailored to your specific needs. Explore the possibilities of image generation, and consider how you might apply these capabilities in your next project!

← Back to All Articles