Create Stunning Art with the Jonbesga/Naigore Cognitive Actions

24 Apr 2025
Create Stunning Art with the Jonbesga/Naigore Cognitive Actions

In the world of artificial intelligence and creative generation, the Jonbesga/Naigore API offers a powerful way to generate images inspired by Nagore's unique artistic style. This set of Cognitive Actions provides developers with pre-built capabilities that can be seamlessly integrated into applications, enabling the creation of custom images with a variety of configurations. By leveraging these actions, developers can enhance their applications' functionality, offering users personalized and artistic content generation.

Prerequisites

Before diving into the integration of the Jonbesga/Naigore Cognitive Actions, ensure you have the following:

  1. An API key for the Cognitive Actions platform to authenticate your requests.
  2. Basic knowledge of JSON structure, as you will be constructing input payloads in this format.
  3. A development environment set up for making HTTP requests (e.g., using Python's requests library).

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

Cognitive Actions Overview

Generate Image with Nagore's Style

The Generate Image with Nagore's Style action allows you to create stunning images using a fine-tuned FLUX.1 model inspired by Nagore's art. This action supports various customizations like aspect ratio, resolution, and output format, along with advanced features such as image-to-image processing and inpainting.

Input

The input for this action is structured as follows:

  • Required Fields:
    • prompt: A descriptive text that guides the image generation.
  • Optional Fields:
    • mask: A URI for an image mask (for inpainting).
    • seed: An integer for setting a random seed (reproducibility).
    • image: A URI for an input image (for image-to-image processing).
    • model: Specifies the inference model (default: "dev").
    • width: The width of the generated image (if aspect ratio is custom).
    • height: The height of the generated image (if aspect ratio is custom).
    • aspectRatio: The aspect ratio of the image (default: "1:1").
    • outputFormat: The desired format for the output image (default: "webp").
    • guidanceScale: A numerical value influencing the image's realism.
    • outputQuality: The quality of the output image (0-100).
    • promptStrength: A factor influencing how much the prompt affects the image.
    • numberOfOutputs: The number of images to generate (default: 1).
    • numberOfInferenceSteps: Steps for denoising (default: 28).

Here is an example of the input JSON payload:

{
  "model": "dev",
  "prompt": "In the style of NGR, a cartoon drawing of a cat is shown. The cat is wearing a hat and is sitting inside a bowl. The cat has a surprised look on its face and is looking upwards. The bowl is placed on a surface, and the cat is the main focus of the image.",
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "loraWeightScale": 1,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 28,
  "additionalLoraWeightScale": 1
}

Output

The output of this action typically returns a URL to the generated image. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/171fa6c0-ea86-404f-bdcf-165b22e73951/540923aa-c0ec-4a68-a55a-b756cce9a6a0.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to invoke the Generate Image with Nagore's Style 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 = "2c091835-e128-4d89-8443-1857727ca71c"  # Action ID for Generate Image with Nagore's Style

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "In the style of NGR, a cartoon drawing of a cat is shown. The cat is wearing a hat and is sitting inside a bowl. The cat has a surprised look on its face and is looking upwards. The bowl is placed on a surface, and the cat is the main focus of the image.",
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "promptStrength": 0.8,
    "loraWeightScale": 1,
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 28,
    "additionalLoraWeightScale": 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 action_id corresponds to the Generate Image with Nagore's Style action, and the payload is structured according to the input schema. The endpoint URL and request structure are illustrative and may vary based on the actual implementation.

Conclusion

The Jonbesga/Naigore Cognitive Actions offer developers an exciting opportunity to integrate advanced image generation capabilities into their applications. By utilizing the Generate Image with Nagore's Style action, you can create beautiful images tailored to specific prompts and artistic styles. As you explore these capabilities, consider experimenting with different parameters to achieve the desired results, and think about the various use cases where such artistic generation can enhance user engagement. Happy coding!

← Back to All Articles