Enhance Your Applications with Image Processing: Integrating the anjakuzev/jas Cognitive Actions

22 Apr 2025
Enhance Your Applications with Image Processing: Integrating the anjakuzev/jas Cognitive Actions

In today's digital landscape, the ability to process and manipulate images is essential for many applications, from art generation to content creation. The anjakuzev/jas specification offers powerful Cognitive Actions that enable developers to integrate advanced image processing capabilities into their applications seamlessly. In this article, we'll explore the "Generate Inpainted Image" action, which allows developers to create modified images while preserving specific non-target areas based on an input mask.

Prerequisites

Before diving into the implementation, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic knowledge of JSON and Python for making API calls.
  • Familiarity with image processing concepts can be beneficial.

To authenticate your requests, you will typically pass your API key in the request headers, allowing you to access the Cognitive Actions securely.

Cognitive Actions Overview

Generate Inpainted Image

The Generate Inpainted Image action allows you to create images with specific sections modified while keeping non-target areas intact. This action is particularly useful for tasks that require editing or enhancing parts of an image without altering the entire content.

Category: Image Processing

Input

The input for this action is structured as a JSON object, featuring several configurable parameters:

  • mask (string, required): URI of the input mask used in inpaint mode. Black areas remain unchanged, while white areas are repainted.
  • seed (integer, optional): Seed for random number generation. Leave blank for automatic randomization.
  • image (string, required): URI of the input image, applicable for img2img or inpaint mode processing.
  • width (integer, optional): Desired width of the output image in pixels. Default is 1024.
  • height (integer, optional): Desired height of the output image in pixels. Default is 1024.
  • prompt (string, optional): Text prompt describing the desired output image. Default is "An astronaut riding a rainbow unicorn".
  • refine (string, optional): Select the refinement style ('no_refiner', 'expert_ensemble_refiner', 'base_image_refiner'). Default is 'no_refiner'.
  • loraScale (number, optional): Scale factor for LoRA models, ranging from 0 to 1. Default is 0.6.
  • scheduler (string, optional): Select the scheduler type for the denoising process. Default is 'K_EULER'.
  • numOutputs (integer, optional): Specify the number of output images (1 to 4). Default is 1.
  • guidanceScale (number, optional): Guidance scale for classifier-free guidance, ranging from 1 to 50. Default is 7.5.
  • negativePrompt (string, optional): Text prompt for specifying undesirable elements in the output.
  • promptStrength (number, optional): Strength of the prompt effect in img2img or inpaint mode, ranging from 0 to 1. Default is 0.8.
  • numInferenceSteps (integer, optional): Total number of steps for the denoising process, ranging from 1 to 500. Default is 50.
  • applyWatermark (boolean, optional): If enabled, applies a watermark to identify generated images. Default is true.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "front shot, portrait of TOK at home in a hoodie, natural skin, daylight, (cinematic, film grain:1.1)",
  "refine": "no_refiner",
  "loraScale": 1,
  "scheduler": "KarrasDPM",
  "numOutputs": 1,
  "guidanceScale": 7.5,
  "highNoiseFrac": 0.8,
  "applyWatermark": true,
  "negativePrompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
  "promptStrength": 1,
  "numInferenceSteps": 50
}

Output

The output of this action typically returns a URL to the generated inpainted image. In case of errors, the response may include error messages detailing what went wrong.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/8a9cdbdf-d620-4908-bf8f-9b853c4e7399/5314f0c6-4904-4d71-80e6-9589b1081ab1.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python snippet demonstrating how to call the Cognitive Actions execution endpoint for the "Generate Inpainted Image" 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 = "84e6fb35-c2d4-43f2-9a7f-e1ff7083f0f2"  # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "front shot, portrait of TOK at home in a hoodie, natural skin, daylight, (cinematic, film grain:1.1)",
    "refine": "no_refiner",
    "loraScale": 1,
    "scheduler": "KarrasDPM",
    "numOutputs": 1,
    "guidanceScale": 7.5,
    "highNoiseFrac": 0.8,
    "applyWatermark": True,
    "negativePrompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
    "promptStrength": 1,
    "numInferenceSteps": 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 code snippet, you will find the necessary components to send a request to the Cognitive Actions endpoint, including the action ID and a structured input payload. Remember that the endpoint URL and request structure are illustrative, and you should adapt them based on your actual implementation requirements.

Conclusion

The anjakuzev/jas Cognitive Actions provide developers with robust tools for image processing, allowing for creative and practical applications. By integrating the "Generate Inpainted Image" action into your projects, you can enhance your applications with dynamic image manipulation capabilities. As you explore these actions further, consider the various parameters and configurations available to tailor the results to your specific needs. Happy coding!

← Back to All Articles