Unlock Creative Potential: Integrating Image Generation with okostadsjunior/ninicollyloli Cognitive Actions

21 Apr 2025
Unlock Creative Potential: Integrating Image Generation with okostadsjunior/ninicollyloli Cognitive Actions

In the ever-evolving landscape of artificial intelligence, the ability to generate images based on user-defined prompts has become a game-changer for developers. The okostadsjunior/ninicollyloli Cognitive Actions provide a powerful toolset to create stunning visuals through a sophisticated image generation process. With features like inpainting, customizable settings, and optimized performance modes, these actions enable developers to elevate their applications to new heights.

Prerequisites

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

  • API Key: Secure access to the Cognitive Actions platform by obtaining your API key.
  • Basic Setup: Familiarity with making API requests in your preferred programming language (e.g., Python).
  • Conceptual Understanding: A grasp of JSON formatting and how to structure requests.

Authentication is typically handled by including your API key in the request headers, allowing you to access the capabilities of the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting

Description: This action allows you to create an image from a textual prompt, with optional inpainting capabilities for modifying existing images. It supports various features including optimized quality and speed modes, LoRA weights, and customizable output aspects.

Category: image-generation

Input: The input schema requires a JSON object with the following properties:

  • prompt (required): A descriptive text string for the image you want to generate.
  • mask (optional): An image mask for inpainting mode.
  • seed (optional): A random seed for reproducibility.
  • image (optional): An input image for image-to-image or inpainting mode.
  • width (optional): Width of the generated image (only if aspect_ratio is custom).
  • height (optional): Height of the generated image (only if aspect_ratio is custom).
  • loraWeights (optional): LoRA weights to enhance generation.
  • outputCount (optional): Number of output images to generate (default is 1, max is 4).
  • imageQuality (optional): Quality of the output images, ranging from 0 to 100.
  • promptImpact (optional): Strength of the prompt in image generation.
  • loraIntensity (optional): Intensity of the main LoRA application.
  • denoisingSteps (optional): Steps for denoising, affecting image detail.
  • inferenceModel (optional): Model type for inference (default is "dev").
  • imageResolution (optional): Approximate megapixels for the image.
  • imageAspectRatio (optional): Aspect ratio of the image (default is "1:1").
  • optimizeForSpeed (optional): Boolean to optimize for speed.
  • guidanceIntensity (optional): Scale for guidance during generation.
  • imageOutputFormat (optional): Format of the output images (default is "webp").
  • bypassSafetyChecker (optional): Option to disable the safety checker.
  • additionalLoraWeights (optional): Additional LoRA weights for enhanced generation.
  • additionalLoraIntensity (optional): Extra intensity for additional LoRA application.

Example Input:

{
  "prompt": "motion picture film still ninicollyloli (long red hair, brown eyes, thin waist thick thighs, perfect body) wears swimwear, on the beach, knee-deep water. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, beautiful, film grain, grainy",
  "outputCount": 4,
  "imageQuality": 100,
  "loraIntensity": 1,
  "denoisingSteps": 28,
  "inferenceModel": "dev",
  "imageAspectRatio": "1:1",
  "guidanceIntensity": 3.5,
  "imageOutputFormat": "png",
  "additionalLoraIntensity": 0.8
}

Output: The action typically returns an array of URLs pointing to the generated images. Here’s an example of what you might receive:

[
  "https://assets.cognitiveactions.com/invocations/fdc8242b-c94f-4a1f-8e58-5ac47e7ad340/3f446a5c-fa50-4b60-93c5-869b97fe27f4.png",
  "https://assets.cognitiveactions.com/invocations/fdc8242b-c94f-4a1f-8e58-5ac47e7ad340/6315bceb-5124-4fdd-b3b0-96cd229cac3f.png",
  "https://assets.cognitiveactions.com/invocations/fdc8242b-c94f-4a1f-8e58-5ac47e7ad340/ea52043f-99cd-4ef4-bdb3-25f719ecb137.png",
  "https://assets.cognitiveactions.com/invocations/fdc8242b-c94f-4a1f-8e58-5ac47e7ad340/33fa764d-3357-4920-9dee-8559929cefba.png"
]

Conceptual Usage Example (Python): Here’s how you might call the Generate Image with Inpainting action using Python:

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 = "ee76a1bc-4898-46aa-885e-485abd9367b3" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "motion picture film still ninicollyloli (long red hair, brown eyes, thin waist thick thighs, perfect body) wears swimwear, on the beach, knee-deep water. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, beautiful, film grain, grainy",
    "outputCount": 4,
    "imageQuality": 100,
    "loraIntensity": 1,
    "denoisingSteps": 28,
    "inferenceModel": "dev",
    "imageAspectRatio": "1:1",
    "guidanceIntensity": 3.5,
    "imageOutputFormat": "png",
    "additionalLoraIntensity": 0.8
}

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}
    )
    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}")

This Python snippet effectively demonstrates how to structure your input and call the Cognitive Actions endpoint. Remember, the endpoint URL and request structure are illustrative; ensure you adjust them as needed based on your application context.

Conclusion

The okostadsjunior/ninicollyloli Cognitive Actions offer an exciting opportunity for developers to harness the power of image generation. With features like customizable prompts, inpainting capabilities, and flexible output settings, you can create unique and engaging visuals for your projects. As you explore these actions, consider experimenting with different parameters to unlock the full potential of your creative applications!

← Back to All Articles