Generate Stunning Images with the jiownt/atomaus Cognitive Action

24 Apr 2025
Generate Stunning Images with the jiownt/atomaus Cognitive Action

In the ever-evolving world of artificial intelligence, the jiownt/atomaus API provides developers with powerful Cognitive Actions for image generation. One such action, Generate Image with Inpainting, allows users to create highly detailed images by utilizing specified image masks and prompts. This action not only enhances customization of image attributes such as size and aspect ratio but also optimizes quality and speed through different model configurations. In this article, we will explore how to leverage this Cognitive Action to bring your creative visions to life.

Prerequisites

Before diving into the action's capabilities, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be required for authentication.
  • Basic knowledge of making HTTP requests and handling JSON data.

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

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows developers to generate images by combining various attributes, including prompts and image masks. This action falls under the image-generation category and is particularly useful for creating compelling visual content.

Input

The action requires a JSON payload structured as follows:

  • prompt (required): A detailed string that describes the image to be generated. Including a trigger word can help activate specific styles in the generated output.
  • mask (optional): A URI pointing to an image mask for inpainting. This will override width, height, and aspect ratio settings.
  • image (optional): A URI for an input image to facilitate image-to-image transformation.
  • model (optional): Specifies the model type to use for generation, either "dev" for quality or "schnell" for speed.
  • width (optional): The width of the generated image, applicable only if custom aspect ratio is selected.
  • height (optional): The height of the generated image, applicable only if custom aspect ratio is selected.
  • imageSize (optional): Specifies the approximate number of megapixels for the output image.
  • imageFormat (optional): The format of the output image (e.g., "webp", "jpg", "png").
  • outputCount (optional): Number of images to generate.
  • imageQuality (optional): Quality level for saving images, ranging from 0 to 100.
  • loraIntensity (optional): Adjusts the application strength of LoRA weights.
  • enableFastMode (optional): A boolean to enable faster predictions.
  • promptIntensity (optional): A strength value for the prompt when using image-to-image.
  • guidanceStrength (optional): Scale for guiding the diffusion process.
  • imageAspectRatio (optional): Defines the aspect ratio for the generated image.
  • inferenceStepCount (optional): Number of steps for denoising, impacting image detail.
  • safetyCheckerDisabled (optional): Flag to disable safety checks for images.

Here is an example of the JSON payload you would use to invoke the action:

{
    "model": "dev",
    "prompt": "\"A hyper-realistic digital illustration of ATOMAUS in a Grand Theft Auto V-inspired setting...\"",
    "imageSize": "1",
    "imageFormat": "webp",
    "outputCount": 4,
    "imageQuality": 80,
    "loraIntensity": 1,
    "enableFastMode": false,
    "promptIntensity": 0.8,
    "guidanceStrength": 3,
    "imageAspectRatio": "1:1",
    "inferenceStepCount": 28,
    "additionalLoraIntensity": 1
}

Output

When you successfully execute the action, it will return a list of image URLs, as shown in the example below:

[
    "https://assets.cognitiveactions.com/invocations/34469f05-29ef-4fd3-92db-85b77622a012/97c35846-88ac-405f-83ea-f54b6d16ec20.webp",
    "https://assets.cognitiveactions.com/invocations/34469f05-29ef-4fd3-92db-85b77622a012/085bb588-d64b-42f2-8dff-a5b7a79847b9.webp",
    "https://assets.cognitiveactions.com/invocations/34469f05-29ef-4fd3-92db-85b77622a012/f9e5c828-e83d-4cef-a577-35f4eec942b5.webp",
    "https://assets.cognitiveactions.com/invocations/34469f05-29ef-4fd3-92db-85b77622a012/697f0d41-3247-4dc2-a31a-72c699b0f695.webp"
]

The response contains a list of URLs pointing to the generated images, allowing you to access your creations directly.

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to call the Generate Image with Inpainting action through a hypothetical Cognitive Actions API endpoint:

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 = "64b3272a-f8ad-4da6-a4d9-a2b843da06a4"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "\"A hyper-realistic digital illustration of ATOMAUS in a Grand Theft Auto V-inspired setting...\"",
    "imageSize": "1",
    "imageFormat": "webp",
    "outputCount": 4,
    "imageQuality": 80,
    "loraIntensity": 1,
    "enableFastMode": False,
    "promptIntensity": 0.8,
    "guidanceStrength": 3,
    "imageAspectRatio": "1:1",
    "inferenceStepCount": 28,
    "additionalLoraIntensity": 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 snippet:

  • You'll replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The action_id is set to the ID for Generate Image with Inpainting.
  • The payload contains all necessary input fields as per the action's requirements.

Conclusion

The jiownt/atomaus Cognitive Action for image generation opens up a world of creative possibilities for developers. By understanding how to effectively utilize the Generate Image with Inpainting action, you can create stunning and tailored images that meet your project's needs. Consider experimenting with different prompts, model types, and settings to push the boundaries of your visual content. Happy coding!

← Back to All Articles