Generate Stunning Images with the Impetus Design Cognitive Actions

24 Apr 2025
Generate Stunning Images with the Impetus Design Cognitive Actions

In the world of digital creativity, the ability to generate images from textual prompts and existing visuals can significantly enhance applications across various domains. The impetusdesign/vhx-gzp provides a powerful Cognitive Action that empowers developers to create images based on textual descriptions and input images. This guide will explore how to utilize the Generate Image with Prompt action, detailing its capabilities, input requirements, and how to implement it in your applications.

Prerequisites

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

  • API Key: You'll need an API key for accessing the Cognitive Actions platform. This key is typically passed in the request headers for authentication.
  • Development Environment: Set up your development environment to make HTTP requests. Python with the requests library is a recommended choice for this guide.

Cognitive Actions Overview

Generate Image with Prompt

The Generate Image with Prompt action allows you to create images based on a combination of a textual prompt and an existing image. This action is particularly useful for applications that require dynamic image generation tailored to user inputs.

Input

The action expects a JSON object containing the following fields:

  • image (required): The URI of the input image to be used in the generation process.
  • seed (optional): A random integer to ensure reproducibility of image generation (default: 92).
  • prompt (optional): A textual prompt guiding the image generation (default: empty string).
  • guidanceScale (optional): Determines how closely the generated image adheres to the prompt (default: 7).
  • ipAdapterScale (optional): Influences the image generation process (default: 0.5).
  • controlNetScale (optional): Affects guidance during image generation (default: 0.5).
  • numberOfOutputs (optional): Specifies how many images to generate (default: 1).
  • numberOfInferenceSteps (optional): The number of steps for refining the image (default: 10).
Example Input
{
  "seed": 92,
  "image": "https://replicate.delivery/pbxt/MYqna52R9iABrM3HEJUKJwCe1lYaXPMJcwmviuhwtTZtvChs/0.png",
  "prompt": "",
  "guidanceScale": 7,
  "ipAdapterScale": 0.5,
  "controlNetScale": 0.5,
  "numberOfInferenceSteps": 10
}

Output

The action returns an array of image URLs generated based on the provided parameters. Here’s an example of the expected output:

Example Output
[
  "https://assets.cognitiveactions.com/invocations/ddee3699-1583-4457-8d49-34d096dfc295/f2bcef73-4170-4dbc-a525-a7972ecf10b9.png"
]

Conceptual Usage Example (Python)

Here’s how you can call the Generate Image with Prompt 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 = "84b0af1f-1f0a-4a0a-80cc-32325ff7d71a"  # Action ID for Generate Image with Prompt

# Construct the input payload based on the action's requirements
payload = {
    "seed": 92,
    "image": "https://replicate.delivery/pbxt/MYqna52R9iABrM3HEJUKJwCe1lYaXPMJcwmviuhwtTZtvChs/0.png",
    "prompt": "",
    "guidanceScale": 7,
    "ipAdapterScale": 0.5,
    "controlNetScale": 0.5,
    "numberOfInferenceSteps": 10
}

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 of the action. The endpoint URL and request structure are illustrative and may vary based on the actual implementation.

Conclusion

The Generate Image with Prompt action from the impetusdesign/vhx-gzp offers a robust way to enhance applications with dynamic image generation capabilities. By integrating this action, developers can create visually engaging experiences tailored to user inputs. As a next step, consider exploring additional parameters and experimenting with different prompts and input images to fully leverage the potential of this action in your applications. Happy coding!

← Back to All Articles