Enhance Your Applications with Image Inpainting Using Thyagobsb Cognitive Actions

25 Apr 2025
Enhance Your Applications with Image Inpainting Using Thyagobsb Cognitive Actions

Cognitive Actions under the spec title thyagobsb/thyagogoncalves provide powerful tools for developers looking to integrate advanced image processing capabilities into their applications. One of the standout features is the ability to perform image inpainting, allowing for the generation or modification of images using sophisticated prediction models. This guide will walk you through how to utilize the Perform Image Inpainting action effectively.

Prerequisites

Before you start integrating Cognitive Actions, ensure you have:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with sending HTTP requests and handling JSON data.

Authentication typically involves passing your API key as a header in your requests.

Cognitive Actions Overview

Perform Image Inpainting

The Perform Image Inpainting action allows developers to generate or modify images using a prediction model capable of inpainting and image-to-image transformations. You can choose between two models: the 'dev' model, optimized for quality, or the 'schnell' model, designed for speed.

Input

The required input for this action includes the following fields:

  • prompt (required): A descriptive string for image generation.
  • model (optional): Specifies which model to use for inference, defaulting to "dev".
  • runFast (optional): A boolean to toggle fast predictions.
  • imageFormat (optional): The format of the output image.
  • imageQuality (optional): The quality of the output image (0-100).
  • numberOfOutputs (optional): How many images to generate (1-4).

Here is an example of the input JSON payload:

{
  "model": "dev",
  "prompt": "thyagogoncalves A green-skinned wizard, thyagogoncalves has an aged and weathered face, deeply lined and rough in texture, tinged with an unnatural greenish hue. His piercing golden-yellow eyes glow with an unsettling intensity, framed by thick gray eyebrows. A long, shaggy gray-brown beard cascades down his chest, partially covering a dark, tattered cloak. The hood, made of worn black cloth with frayed edges, casts shadows across his forehead, adding to his enigmatic aura.",
  "runFast": false,
  "imageFormat": "png",
  "imageQuality": 80,
  "loraStrength": 1,
  "guidanceFactor": 3,
  "inferenceSteps": 28,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "imageAspectRatio": "9:16",
  "additionalLoraStrength": 1
}

Output

Upon executing this action, the output will typically consist of a URL pointing to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/4144f020-c408-460b-83d9-4fa2f6c475de/5b5873ed-9956-4063-b24d-99f09db2cf72.png"
]

Conceptual Usage Example (Python)

Here’s how you might structure your Python code to invoke the Perform Image Inpainting action:

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 = "26d93251-d847-45a6-bb92-5b06363cc153" # Action ID for Perform Image Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "thyagogoncalves A green-skinned wizard, thyagogoncalves has an aged and weathered face, deeply lined and rough in texture, tinged with an unnatural greenish hue. His piercing golden-yellow eyes glow with an unsettling intensity, framed by thick gray eyebrows. A long, shaggy gray-brown beard cascades down his chest, partially covering a dark, tattered cloak. The hood, made of worn black cloth with frayed edges, casts shadows across his forehead, adding to his enigmatic aura.",
    "runFast": false,
    "imageFormat": "png",
    "imageQuality": 80,
    "loraStrength": 1,
    "guidanceFactor": 3,
    "inferenceSteps": 28,
    "imageMegapixels": "1",
    "numberOfOutputs": 1,
    "promptIntensity": 0.8,
    "imageAspectRatio": "9:16",
    "additionalLoraStrength": 1
}

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 example, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id variable holds the ID of the Perform Image Inpainting action. The input payload is constructed according to the specified input schema, ensuring all required fields are included.

Conclusion

Integrating the Perform Image Inpainting action from the thyagobsb/thyagogoncalves spec into your application can significantly enhance your image processing capabilities. With options for speed and quality, this action allows for creative and practical applications in various domains, from art generation to image editing. Explore further enhancements by combining this action with additional Cognitive Actions to unlock even more potential in your projects!

← Back to All Articles