Generate Stunning Images with the palosisd/tomnecas Cognitive Actions

22 Apr 2025
Generate Stunning Images with the palosisd/tomnecas Cognitive Actions

In today's digital landscape, creating high-quality images programmatically can enhance applications in numerous ways—from generating artwork to facilitating design workflows. The palosisd/tomnecas API provides a powerful set of Cognitive Actions that leverage advanced image generation techniques, particularly through inpainting. This article will delve into how developers can utilize these actions to create stunning visuals effortlessly.

Prerequisites

Before you can start using the Cognitive Actions provided by the palosisd/tomnecas API, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic knowledge of JSON format and making HTTP requests.

For authentication, you typically pass your API key in the request headers. This will enable you to securely access the actions available in the API.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows developers to create high-quality images using inpainting techniques. This action supports various customizable parameters, enabling fine-tuning for diverse use cases. With the option to leverage the fast generation model, it optimizes performance while maintaining quality.

Input

The input for the Generate Image with Inpainting action consists of several fields, where prompt is the only required field. Here’s a breakdown of the input schema:

  • prompt: string (required) - A detailed description of the image to generate.
  • mask: string (optional) - URI for an image mask, overriding dimensions.
  • seed: integer (optional) - Random seed for reproducibility.
  • image: string (optional) - Input image for manipulation.
  • model: string (default: "dev") - Model to use for inference.
  • width: integer (optional, max: 1440) - Width of the generated image.
  • height: integer (optional, max: 1440) - Height of the generated image.
  • megapixels: string (default: "1") - Approximate megapixels of the image.
  • imageFormat: string (default: "webp") - Output image format.
  • outputCount: integer (default: 1, min: 1, max: 4) - Number of images to generate.
  • imageQuality: integer (default: 80, min: 0, max: 100) - Quality of the output images.
  • promptImpact: number (default: 0.8) - Strength of the prompt.
  • guidanceScale: number (default: 3) - Guidance scale for generation.
  • loraIntensity: number (default: 1) - Intensity of LoRA application.
  • acceleratedMode: boolean (default: false) - Enable for faster predictions.
  • imageAspectRatio: string (default: "1:1") - Aspect ratio for the image.
  • inferenceStepsCount: integer (default: 28) - Number of denoising steps.
  • additionalLoraIntensity: number (default: 1) - Additional LoRA intensity.

Example Input:

{
  "model": "dev",
  "prompt": "A picture of mexican TOMASNECAS with his glasses next to aliens, realistic lighting, realostoc picture, amazing lighting, amazing image, cool image",
  "megapixels": "1",
  "imageFormat": "webp",
  "outputCount": 3,
  "imageQuality": 80,
  "promptImpact": 0.8,
  "guidanceScale": 3,
  "loraIntensity": 1,
  "acceleratedMode": false,
  "imageAspectRatio": "1:1",
  "inferenceStepsCount": 28,
  "additionalLoraIntensity": 1
}

Output

The output of this action is an array of URLs that point to the generated images. Each URL corresponds to an output image based on the input parameters provided.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/9cf66da1-455e-4477-a5ee-f0966f00c4b5/b8690931-ed86-40c8-b4cb-2e31477f54dd.webp",
  "https://assets.cognitiveactions.com/invocations/9cf66da1-455e-4477-a5ee-f0966f00c4b5/66b42c4c-1ebd-4a8b-bab7-80ca84872afc.webp",
  "https://assets.cognitiveactions.com/invocations/9cf66da1-455e-4477-a5ee-f0966f00c4b5/bc0441d6-7ce7-42a5-a10c-fdcf03f3c71e.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet that demonstrates how a developer might call the Generate Image with Inpainting action using the hypothetical Cognitive Actions 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 = "86553709-e2bd-434d-9723-ff2b97d78fd0"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "A picture of mexican TOMASNECAS with his glasses next to aliens, realistic lighting, realostoc picture, amazing lighting, amazing image, cool image",
    "megapixels": "1",
    "imageFormat": "webp",
    "outputCount": 3,
    "imageQuality": 80,
    "promptImpact": 0.8,
    "guidanceScale": 3,
    "loraIntensity": 1,
    "acceleratedMode": False,
    "imageAspectRatio": "1:1",
    "inferenceStepsCount": 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 code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is structured according to the required input fields for the action, and the response is printed in a readable format.

Conclusion

The palosisd/tomnecas Cognitive Actions provide powerful tools for generating high-quality images with customizable parameters. By leveraging the Generate Image with Inpainting action, developers can create visually stunning outputs tailored to their specific requirements. Next steps could include experimenting with different prompts, image formats, and models to fully harness the capabilities of this API and integrate it seamlessly into various applications. Happy coding!

← Back to All Articles