Generate Stunning Images with the Omerai Cognitive Actions

22 Apr 2025
Generate Stunning Images with the Omerai Cognitive Actions

In the realm of AI and machine learning, image generation has taken significant strides, enabling developers to create unique visuals based on textual prompts. The Omerai spec offers powerful Cognitive Actions that leverage advanced models to generate images with customizable parameters. This integration allows developers to enhance their applications with dynamic, high-quality images, enriching user experiences and providing creative solutions.

Prerequisites

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

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with making HTTP requests and handling JSON data.

Authentication typically involves passing your API key in the headers of your requests, ensuring secure access to the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with LoRA Model

Description: This action generates images using a LoRA model, allowing for extensive customization of parameters such as prompt strength, image quality, aspect ratio, and inference steps. It supports fast generation modes and can output multiple images.

Category: Image Generation

Input

The input for this action requires a JSON object structured as follows:

  • Required:
    • prompt (string): A descriptive text prompt for the image generation.
  • Optional:
    • mask (string): URI of the image mask for inpainting mode.
    • seed (integer): A seed for reproducible results.
    • image (string): Input image for image-to-image transformations.
    • width (integer): Width of the generated image (for custom aspect ratios).
    • height (integer): Height of the generated image (for custom aspect ratios).
    • loraScale (number): Intensity of the LoRA effect.
    • megapixels (string): Approximate number of megapixels for the generated image.
    • outputCount (integer): Number of images to generate (1 to 4).
    • guidanceScale (number): Guidance scale for the diffusion process.
    • inferenceModel (string): Model to use for inference (default is "dev").
    • inferenceSteps (integer): Number of denoising iterations.
    • promptStrength (number): Strength of the prompt in image-to-image transformations.
    • imageAspectRatio (string): Aspect ratio of the generated image.
    • imageOutputFormat (string): Format of the generated images (webp, jpg, png).
    • imageOutputQuality (integer): Quality of the output images (0 to 100).
    • additionalLoraScale (number): Intensity of additional LoRA application.
    • accelerateGeneration (boolean): Enable faster predictions.
    • disableSafetyChecker (boolean): Turn off the safety checker.
    • additionalLoraWeights (string): Additional sources for LoRA weights.

Example Input:

{
  "prompt": "omerai a man with eyeglass is looking to the camera in the car",
  "loraScale": 1,
  "megapixels": "1",
  "outputCount": 1,
  "guidanceScale": 3,
  "inferenceModel": "dev",
  "inferenceSteps": 28,
  "promptStrength": 0.8,
  "imageAspectRatio": "16:9",
  "imageOutputFormat": "jpg",
  "imageOutputQuality": 80,
  "additionalLoraScale": 1,
  "accelerateGeneration": false
}

Output

The output of this action will typically return a list of URLs pointing to the generated images. Here’s an example:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/99030341-4f44-4b12-84be-0920002a2429/703d963f-07e5-4277-ba49-b4bd99ab5159.jpg"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how a developer might invoke the 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 = "f892195f-9a6e-4302-95f0-5b2c389bb791"  # Action ID for Generate Image with LoRA Model

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "omerai a man with eyeglass is looking to the camera in the car",
    "loraScale": 1,
    "megapixels": "1",
    "outputCount": 1,
    "guidanceScale": 3,
    "inferenceModel": "dev",
    "inferenceSteps": 28,
    "promptStrength": 0.8,
    "imageAspectRatio": "16:9",
    "imageOutputFormat": "jpg",
    "imageOutputQuality": 80,
    "additionalLoraScale": 1,
    "accelerateGeneration": False
}

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}")

In this code, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the action for generating images, and the payload is structured according to the specified input schema. This snippet serves as a guideline for integrating the Cognitive Action into your application.

Conclusion

The Omerai Cognitive Actions empower developers to create visually stunning images from textual prompts, with a wealth of customization options that enhance creativity and functionality. By leveraging these actions, you can integrate advanced image generation capabilities into your applications, opening up new possibilities for user engagement and content creation. Start experimenting with these Cognitive Actions today and see how they can elevate your projects!

← Back to All Articles