Harness Image Generation with the Ravenssss Cognitive Actions

21 Apr 2025
Harness Image Generation with the Ravenssss Cognitive Actions

In today's digital landscape, the ability to generate images using AI is transforming how developers create content and applications. The Ravenssss Cognitive Actions provide a powerful way to generate images tailored to specific requirements using AI models. With customizable parameters that allow for detailed adjustments, these actions can significantly enhance your application's visual capabilities. In this blog post, we'll dive into the Generate Image Using AI Model action, exploring how to leverage its capabilities effectively.

Prerequisites

Before you can start using the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be required for authentication.
  • Basic knowledge of JSON and Python for constructing requests and handling responses.

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

Cognitive Actions Overview

Generate Image Using AI Model

The Generate Image Using AI Model action allows for the creation of images using AI models with a variety of customizable parameters, including aspect ratio, dimensions, and prompt strength. This action is part of the image-generation category and provides flexibility for users seeking detailed or faster results.

Input

The input for this action requires several fields, with the prompt being mandatory. Below is a breakdown of the input schema along with an example:

{
  "prompt": "A photo of raven in an ultra-realistic, high-resolution photograph dressed in a detailed Wonder Woman costume, looking directly at the camera with a determined expression. She holds a gleaming sword in her right hand and a neatly printed sign in her left hand that reads 'Raven Property Management'. The setting is an urban environment during daylight, captured with natural lighting and sharp focus. The image features vivid colors and intricate details to achieve photorealism",
  "aspectRatio": "1:1",
  "outputCount": 4,
  "imageQuality": 100,
  "outputFormat": "jpg",
  "guidanceScale": 3,
  "loraIntensity": 1,
  "inferenceModel": "dev",
  "inferenceSteps": 45,
  "promptStrength": 1,
  "additionalLoraIntensity": 2
}

Key Input Fields:

  • prompt: Instruction for image creation (required).
  • aspectRatio: Defines the aspect ratio (default: 1:1).
  • outputCount: Number of images to generate (default: 1).
  • imageQuality: Quality of generated images from 0 to 100 (default: 80).
  • outputFormat: Format of output images (default: webp).
  • guidanceScale: Scale for the diffusion process (default: 3).
  • inferenceModel: Selects the model for inference, either dev or schnell (default: dev).
  • inferenceSteps: Number of denoising steps (default: 28).
  • promptStrength: Strength of the prompt (default: 0.8).

Output

When the action is executed successfully, it returns an array of URLs pointing to the generated images. Here’s an example of the expected output:

[
  "https://assets.cognitiveactions.com/invocations/a3af25bf-821e-4a5d-81b1-ada245e6a368/05f5a4dc-896f-4cf5-ad59-5940e06affd5.jpg",
  "https://assets.cognitiveactions.com/invocations/a3af25bf-821e-4a5d-81b1-ada245e6a368/75167a79-c361-4006-a717-e7696b8acb7b.jpg",
  "https://assets.cognitiveactions.com/invocations/a3af25bf-821e-4a5d-81b1-ada245e6a368/20e85507-30cf-41e1-a9f5-63d020b5a20c.jpg",
  "https://assets.cognitiveactions.com/invocations/a3af25bf-821e-4a5d-81b1-ada245e6a368/4faab298-0c59-4691-b0c9-d159ff1bbbeb.jpg"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might call the Generate Image Using AI Model 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 = "991e0a00-ea0c-4096-97e4-a35fa0950c0a" # Action ID for Generate Image Using AI Model

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "A photo of raven in an ultra-realistic, high-resolution photograph dressed in a detailed Wonder Woman costume, looking directly at the camera with a determined expression. She holds a gleaming sword in her right hand and a neatly printed sign in her left hand that reads 'Raven Property Management'. The setting is an urban environment during daylight, captured with natural lighting and sharp focus. The image features vivid colors and intricate details to achieve photorealism",
    "aspectRatio": "1:1",
    "outputCount": 4,
    "imageQuality": 100,
    "outputFormat": "jpg",
    "guidanceScale": 3,
    "loraIntensity": 1,
    "inferenceModel": "dev",
    "inferenceSteps": 45,
    "promptStrength": 1,
    "additionalLoraIntensity": 2
}

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}")

This code snippet demonstrates how to structure your input payload, set the headers for authentication, and handle the response from the Cognitive Actions API. Remember to replace the placeholder values with your actual API key and endpoint.

Conclusion

The Ravenssss Cognitive Actions open up a world of possibilities for developers looking to integrate advanced image generation capabilities into their applications. By leveraging the Generate Image Using AI Model action, you can create stunning visuals tailored to your specific needs. Explore these actions further, and consider how they can enhance your projects, whether for creative content, marketing, or unique application features. Happy coding!

← Back to All Articles