Generate Stunning Images with Ronyoren/Alma Cognitive Actions

22 Apr 2025
Generate Stunning Images with Ronyoren/Alma Cognitive Actions

In the world of artificial intelligence and machine learning, image generation has emerged as an exciting frontier. The Ronyoren/Alma API brings together a powerful set of Cognitive Actions designed for seamless image generation, particularly through advanced inpainting techniques. These actions allow developers to create customizable and high-quality images by harnessing AI's capabilities for specific prompts. Whether you’re building an application that requires creative illustrations or enhancing existing images, these pre-built actions can significantly streamline your development process.

Prerequisites

Before diving into the integration of the Ronyoren/Alma Cognitive Actions, you'll need a few essential items:

  • An API key for accessing the Cognitive Actions platform.
  • Understanding of how to configure HTTP headers for authentication, typically by including the API key in the request headers.

Cognitive Actions Overview

Generate Image Using Inpainting

The Generate Image Using Inpainting action allows developers to generate images by utilizing an inpainting model. This method supports various customizable parameters, enabling enhanced image outputs based on specific requirements.

Input

The input schema for this action is defined as follows:

  • prompt (required): A textual prompt guiding the image generation.
  • mask (optional): URI of an image mask for inpainting.
  • seed (optional): Random seed for generating deterministic outputs.
  • image (optional): URI of an input image for transformations.
  • model (optional): Select model type (dev or schnell).
  • width (optional): Width of the generated image (must be a multiple of 16).
  • goFast (optional): Boolean to enable fast predictions.
  • height (optional): Height of the generated image (must be a multiple of 16).
  • outputCount (optional): Number of images to generate (1-4).
  • imageQuality (optional): Quality level of the output image (0-100).
  • guidanceScale (optional): Strength of guidance during the generation process.
  • mainLoraScale (optional): Intensity of the primary LoRA effects.
  • trainedWeights (optional): Specify LoRA weights in various formats.
  • imageMegapixels (optional): Select approximate megapixels for the generated image.
  • denoiseStepCount (optional): Number of steps for denoising during inference.
  • imageAspectRatio (optional): Define aspect ratio for the generated image.
  • imageOutputFormat (optional): Choose output format (WEBP, JPEG, PNG).
  • additionalLoraScale (optional): Adjust the scale of additional LoRA effects.
  • inputPromptStrength (optional): Influence of the prompt in img2img tasks.
  • additionalLoraWeights (optional): Specify additional LoRA weights.
  • safetyCheckerDisabled (optional): Option to disable the safety checker for image generation.

Example Input:

{
  "model": "dev",
  "prompt": "Create a whimsical 3D illustration of Alma smiling and hugs her unicorn at her home",
  "outputCount": 1,
  "imageQuality": 90,
  "guidanceScale": 3.5,
  "mainLoraScale": 1,
  "denoiseStepCount": 28,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "additionalLoraScale": 1,
  "inputPromptStrength": 0.8
}

Output

The expected output of this action is a URL pointing to the generated image. The output typically resembles the following:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/af3e175d-6d75-49b4-8319-df2c41ec96c7/6c945392-3e0e-4a9e-8c39-6748a227b60e.webp"
]

Conceptual Usage Example (Python)

Here's how you might call the Generate Image Using 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 = "ab6895ac-a657-4c97-bf6a-423b971f19f6" # Action ID for Generate Image Using Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "Create a whimsical 3D illustration of Alma smiling and hugs her unicorn at her home",
    "outputCount": 1,
    "imageQuality": 90,
    "guidanceScale": 3.5,
    "mainLoraScale": 1,
    "denoiseStepCount": 28,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "additionalLoraScale": 1,
    "inputPromptStrength": 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} # 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, make sure to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is structured based on the input schema provided, ensuring all necessary parameters are included.

Conclusion

The Ronyoren/Alma Cognitive Actions provide a robust way to generate customized images using advanced inpainting techniques. By leveraging these pre-built actions, developers can create stunning visuals that enhance applications or creative projects with ease. Consider exploring the potential of these actions in your next project to unlock new creative possibilities!

← Back to All Articles