Transform Your Images: Using jschoormans/unstaging to Remove Furniture

24 Apr 2025
Transform Your Images: Using jschoormans/unstaging to Remove Furniture

In the rapidly evolving world of image processing, the jschoormans/unstaging API offers a powerful toolset for developers looking to enhance their applications with innovative image manipulation capabilities. One of the standout features of this API is its Cognitive Action that allows users to remove furniture from images, creating the illusion of an empty space. This functionality is particularly useful for real estate applications, interior design tools, and any platform that benefits from visual clarity.

Prerequisites

To get started with the jschoormans/unstaging API, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Familiarity with making HTTP requests in your programming language of choice.
  • A basic understanding of JSON to structure your input data.

Authentication typically involves including the API key in the headers of your requests, allowing you to securely access the Cognitive Actions.

Cognitive Actions Overview

Remove Furniture from Image

Description: This operation removes furniture from an image, effectively creating an image of an empty room. It accepts an image URI and a text prompt, which guides the image processing to produce a furniture-free environment.

Category: image-processing

Input

To invoke the "Remove Furniture from Image" action, you need to provide the following fields in your JSON payload:

  • image (required): The URI of the input image to be used for conditioning during processing.
  • prompt (required): A text-based input that guides the generation process, describing the intended output.
  • resolution (optional): The desired resolution for the output image (default is 768, range: 256-2048).
  • numInferenceSteps (optional): Specifies the number of denoising steps utilized in the generation process (default is 8, range: 1-50).
  • resolutionConditioning (optional): Defines the resolution of the conditioning image (default is 768, range: 256-2048).

Example Input:

{
  "image": "https://replicate.delivery/pbxt/MYuiIS1geUNr8VVdDvRcnn0igNwrlADa2qKRMMUKOxgkj1QM/ap_21021110795446_custom-fd9247fb6ba93d0716007fe065d4959310b3e6a8.webp",
  "prompt": "empty room, nothing",
  "resolution": 1024,
  "numInferenceSteps": 8,
  "resolutionConditioning": 1024
}

Output

Upon successful execution, the action typically returns a URI pointing to the generated image with the furniture removed.

Example Output:

https://assets.cognitiveactions.com/invocations/fa704240-0874-46ae-8725-559e035cc98c/0bc5db00-5fa1-43f9-a584-3dfcd73a2066.png

Conceptual Usage Example (Python)

Here’s how you might call the "Remove Furniture from Image" action using a conceptual Python snippet:

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 = "8a1f80e7-8861-42fa-92f4-e46294527599"  # Action ID for Remove Furniture from Image

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/MYuiIS1geUNr8VVdDvRcnn0igNwrlADa2qKRMMUKOxgkj1QM/ap_21021110795446_custom-fd9247fb6ba93d0716007fe065d4959310b3e6a8.webp",
    "prompt": "empty room, nothing",
    "resolution": 1024,
    "numInferenceSteps": 8,
    "resolutionConditioning": 1024
}

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 "Remove Furniture from Image" action, and the input payload is structured according to the action's requirements.

Conclusion

The jschoormans/unstaging API provides a powerful means to manipulate images by removing furniture, offering significant value for developers aiming to enhance user experiences in various applications. By leveraging this Cognitive Action, you can create stunning visual content that meets the demands of modern digital environments.

Consider exploring other actions within the API to further enrich your applications and push the boundaries of image processing capabilities.

← Back to All Articles