Transform Your Spaces: Integrating Virtual Staging with Remodela AI Cognitive Actions

22 Apr 2025
Transform Your Spaces: Integrating Virtual Staging with Remodela AI Cognitive Actions

In the world of interior design and real estate, captivating visuals can make all the difference. The remodela-ai/virtual_stagging_demo provides developers with a powerful Cognitive Action that allows for the generation of stunning virtual staging images. With the ability to create design variations based on an initial image and a specified mask, this action opens up new possibilities for enhancing visual presentations. By leveraging pre-built actions, developers can save time and effort while delivering exceptional user experiences.

Prerequisites

Before you start integrating the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic understanding of working with APIs and handling JSON data.

For authentication, you'll typically pass your API key in the request headers to securely access the services.

Cognitive Actions Overview

Generate Virtual Staging Images

Description: This action allows you to create virtual staging images by generating design variations over an initial image using a specified mask. It supports customization with different style prompts and configuration options, including guidance scale, number of outputs, and inference steps.

  • Category: Image Generation

Input

The input for this action requires the following fields:

  • image (string, required): The URI of the initial image to generate variations. Supports images of size 512x512 pixels.
    • Example:
      https://replicate.delivery/pbxt/Ls2EOAL52fVMIITSj479VeyOpyVCNGAZpKzZNMvj3rBScbLW/room.jpg
  • mask (string, required): A black and white image URI used as a mask for inpainting over the provided image. White pixels are inpainted, while black pixels are preserved.
    • Example:
      https://replicate.delivery/pbxt/Ls2EOvrMvSlcDjdCRwBXleruEcia4bqGRYjqjWzM3Kkjfu47/mask_room_black.jpg
  • prompt (string, optional): Select the design style for the generated image. Options include "midCenturyModern", "coastal", "contemporary", "traditional", "modern", "scandinavian", "industrial", and "minimalist". Defaults to "modern".
    • Example:
      modern
  • guidanceScale (number, optional): Defines the scale for classifier-free guidance (1 to 20). Defaults to 7.5.
    • Example:
      15.49
  • negativePrompt (string, optional): List items to avoid in the generated output, enhancing image specificity.
  • numberOfOutputs (integer, optional): Specifies the number of output images to generate (1 to 8). Defaults to 1.
    • Example:
      1
  • numberOfInferenceSteps (integer, optional): Sets the number of denoising steps in the inference process (1 to 500). Defaults to 25.
    • Example:
      25

Example Input:

{
  "mask": "https://replicate.delivery/pbxt/Ls2EOvrMvSlcDjdCRwBXleruEcia4bqGRYjqjWzM3Kkjfu47/mask_room_black.jpg",
  "image": "https://replicate.delivery/pbxt/Ls2EOAL52fVMIITSj479VeyOpyVCNGAZpKzZNMvj3rBScbLW/room.jpg",
  "prompt": "modern",
  "guidanceScale": 15.49,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 25
}

Output

The action typically returns an array of URIs for the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/626fe1af-8da4-4444-8223-11d29a525e4c/8be421d9-29bf-4929-81d0-94ac92d30ce8.png"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Virtual Staging Images 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 = "61bdc241-00ea-4757-9594-494f515bad13"  # Action ID for Generate Virtual Staging Images

# Construct the input payload based on the action's requirements
payload = {
  "mask": "https://replicate.delivery/pbxt/Ls2EOvrMvSlcDjdCRwBXleruEcia4bqGRYjqjWzM3Kkjfu47/mask_room_black.jpg",
  "image": "https://replicate.delivery/pbxt/Ls2EOAL52fVMIITSj479VeyOpyVCNGAZpKzZNMvj3rBScbLW/room.jpg",
  "prompt": "modern",
  "guidanceScale": 15.49,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 25
}

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 action_id corresponds to the "Generate Virtual Staging Images" action. The input payload is structured according to the action's requirements, and the response is printed in a readable format.

Conclusion

The remodela-ai/virtual_stagging_demo Cognitive Action provides an innovative way to enhance interior design images, making it easier for developers to integrate advanced visual capabilities into their applications. By utilizing the Generate Virtual Staging Images action, you can create compelling and varied design options that will elevate your project. Consider exploring additional use cases for virtual staging in real estate platforms, e-commerce, or interior design applications to fully leverage this powerful tool!

← Back to All Articles