Generate Stunning Images with Cognitive Actions in drrhinoai/ruby-lora

23 Apr 2025
Generate Stunning Images with Cognitive Actions in drrhinoai/ruby-lora

In the realm of artificial intelligence, image generation has become a fascinating area of exploration. The drrhinoai/ruby-lora API provides powerful Cognitive Actions that allow developers to generate images using LoRA models. By leveraging customizable parameters, you can create stunning visuals tailored to your specific needs. This article will guide you through how to integrate these actions into your applications, enhancing user experiences with generated images.

Prerequisites

To use the Cognitive Actions provided by the drrhinoai/ruby-lora API, you will need:

  • An API key to access the Cognitive Actions platform.
  • Basic familiarity with making HTTP requests and handling JSON data.
  • A development environment set up for making API calls (e.g., Python, Postman).

Authentication typically involves including your API key in the request headers, ensuring secure access to the services.

Cognitive Actions Overview

Generate Image Using LoRA Models

The Generate Image Using LoRA Models action generates images based on customizable parameters like image size, aspect ratio, and prompt strength. You can choose between the 'schnell' model for fast predictions or the 'dev' model for higher quality images.

Input

The input schema for this action requires a JSON object with the following fields:

  • prompt (required): A descriptive text prompt for the image to be generated.
  • mask (optional): URI for image mask in inpainting mode.
  • seed (optional): An integer seed for reproducibility.
  • image (optional): An input image for image-to-image or inpainting mode.
  • width (optional): Width of the generated image (valid when aspect_ratio is set to custom).
  • height (optional): Height of the generated image (valid when aspect_ratio is set to custom).
  • fastMode (optional): Boolean to enable faster predictions.
  • modelType (optional): Choose between 'dev' or 'schnell'.
  • imageFormat (optional): Output format (webp, jpg, png).
  • outputCount (optional): Number of output images to generate.
  • imageQuality (optional): Quality of the generated images, from 0 to 100.
  • promptEffect (optional): Strength of the prompt in image generation.
  • imageResolution (optional): Approximate number of megapixels.
  • imageAspectRatio (optional): Aspect ratio for the generated image (e.g., 16:9, 1:1).
  • diffusionGuidance (optional): Guidance scale for the diffusion process.
  • mainLoraIntensity (optional): Intensity of the main LoRA application.
  • inferenceStepCount (optional): Number of denoising steps.
  • additionalLoraIntensity (optional): Intensity for additional LoRA applications.
  • safetyCheckerDisabled (optional): Disable the safety checker.

Example Input:

{
  "prompt": "AIRUBY is playing the fairy tale character, Cinderella. Her family is using her as a skullery maid, and she is 18 years old, and is currently cleaning out the fireplace, sitting on the floor, cleaning out ashes and placing them in a wooden bucket. The room, furniture and clothing should all reflect the time period of the fairy tale. Photorealistic, exquisite detail",
  "fastMode": false,
  "modelType": "dev",
  "imageFormat": "jpg",
  "outputCount": 1,
  "imageQuality": 100,
  "promptEffect": 0.8,
  "imageResolution": "1",
  "imageAspectRatio": "16:9",
  "diffusionGuidance": 3,
  "mainLoraIntensity": 1,
  "inferenceStepCount": 28,
  "additionalLoraIntensity": 1
}

Output

The output will typically return a list of URLs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/2992018a-1707-46c8-a433-f96d3c9ffd9d/a57cc84a-3a8f-4bbf-bc3a-e72a6bd8c6a7.jpg"
]

Conceptual Usage Example (Python)

Here’s how you might call this 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 = "3ef7f021-aeb9-4d99-8b97-c0fe0a252d15"  # Action ID for Generate Image Using LoRA Models

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "AIRUBY is playing the fairy tale character, Cinderella. Her family is using her as a skullery maid, and she is 18 years old, and is currently cleaning out the fireplace, sitting on the floor, cleaning out ashes and placing them in a wooden bucket. The room, furniture and clothing should all reflect the time period of the fairy tale. Photorealistic, exquisite detail",
    "fastMode": False,
    "modelType": "dev",
    "imageFormat": "jpg",
    "outputCount": 1,
    "imageQuality": 100,
    "promptEffect": 0.8,
    "imageResolution": "1",
    "imageAspectRatio": "16:9",
    "diffusionGuidance": 3,
    "mainLoraIntensity": 1,
    "inferenceStepCount": 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 variable is structured according to the input schema we discussed, and the request is sent to a hypothetical endpoint for action execution.

Conclusion

The drrhinoai/ruby-lora Cognitive Actions provide a robust way to generate images tailored to your application's needs. With the ability to customize various parameters, you can create unique visuals that enhance user engagement. Consider experimenting with different prompts and settings to discover the best results for your projects. Happy coding!

← Back to All Articles