Generate Stunning Image Variations with pranavred/interior-test Cognitive Actions

21 Apr 2025
Generate Stunning Image Variations with pranavred/interior-test Cognitive Actions

In today's digital landscape, image generation has become an essential tool for developers looking to create unique visual content. The pranavred/interior-test API provides powerful Cognitive Actions designed to facilitate image manipulation and generation. Among these is the Generate Image Variation action, which allows developers to create variations of an input image using advanced img2img techniques. This article will guide you through the capabilities of this action, its input requirements, and how to integrate it into your applications seamlessly.

Prerequisites

Before you start using the Cognitive Actions, ensure you have a valid API key for the Cognitive Actions platform. Authentication typically involves passing your API key in the request headers to gain access to the available actions.

Cognitive Actions Overview

Generate Image Variation

The Generate Image Variation action enables you to generate new variations of an input image while allowing for various customizable parameters, including dimensions, prompt guidance, and the scheduler algorithm. This action supports controlled randomness and can produce multiple outputs, making it a versatile tool for developers looking to enhance their applications with dynamic imagery.

Input

The input for this action is structured as a JSON object with several properties. Here’s a breakdown of the required and optional fields:

  • seed (integer, optional): A random seed value for variation. Leave blank to randomize.
  • image (string, required): URI to the input image for generating variations. If provided, the width and height parameters are ignored.
  • width (integer, optional): Output image width. Defaults to 512. Choices range from 128 to 1024.
  • height (integer, optional): Output image height. Defaults to 512. Choices range from 128 to 1024.
  • prompt (string, optional): Text prompt guiding the image generation. Default is "a photo of cjw".
  • scheduler (string, optional): Scheduler algorithm, defaults to "DDIM".
  • guidanceScale (number, optional): Scale for classifier-free guidance, ranging from 1 to 20. Defaults to 7.5.
  • negativePrompt (string, optional): Elements to exclude from the output.
  • promptStrength (number, optional): Influences the initial image prompt, with 1.0 signifying complete alteration. Defaults to 0.8.
  • numberOfOutputs (integer, optional): Number of output images to generate (1 to 4). Defaults to 1.
  • disableSafetyCheck (boolean, optional): Bypass safety checks if true. Disabled by default.
  • numberOfInferenceSteps (integer, optional): Defines iterations for the denoising process (1 to 500). Defaults to 50.

Here’s an example of the input JSON payload:

{
  "width": 512,
  "height": 512,
  "prompt": "a photo of ixte with balloons, 4k, beautiful",
  "scheduler": "DDIM",
  "guidanceScale": 7.5,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "disableSafetyCheck": false,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns a list of URLs pointing to the generated images. Here’s an example of the output you might receive:

[
  "https://assets.cognitiveactions.com/invocations/57bb03cf-1a6c-408a-a20d-4a3c9bf2bd8f/35fae62a-6e53-4cea-975e-2fbe099dd2ca.png"
]

Conceptual Usage Example (Python)

The following conceptual Python code snippet illustrates how to call the Generate Image Variation action within your application. Remember to replace the placeholders with your actual API key and endpoint.

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 = "bcfb8b8e-e392-4fa6-93ca-bf4681812f5d" # Action ID for Generate Image Variation

# Construct the input payload based on the action's requirements
payload = {
    "width": 512,
    "height": 512,
    "prompt": "a photo of ixte with balloons, 4k, beautiful",
    "scheduler": "DDIM",
    "guidanceScale": 7.5,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "disableSafetyCheck": false,
    "numberOfInferenceSteps": 50
}

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, the action ID is specified for Generate Image Variation, and the input payload is constructed according to the specified schema. The snippet handles the response and potential errors gracefully.

Conclusion

The Generate Image Variation action in the pranavred/interior-test API opens up a world of possibilities for developers looking to enhance their applications with dynamic images. By understanding the input requirements and using the provided examples, you can easily integrate this powerful action into your projects. Consider exploring different prompts and parameters to create stunning visuals tailored to your needs!

← Back to All Articles