Transform Your Interior Design Projects with Cognitive Actions: Generate Stunning Images with Inpainting

23 Apr 2025
Transform Your Interior Design Projects with Cognitive Actions: Generate Stunning Images with Inpainting

In the realm of artificial intelligence, the ability to create and manipulate images based on textual prompts is a game changer. The kjw488/sdxl-demo-ai-interior API offers developers powerful Cognitive Actions that simplify the image generation process, specifically through a unique action: Generate Image with Inpainting. This action enables you to create visually appealing images from descriptions, allowing you to enhance your interior design applications or any project requiring creative visuals.

Prerequisites

To get started with the Cognitive Actions, you'll need an API key from the Cognitive Actions platform. This key is crucial for authenticating your requests. Generally, you will pass the API key in the headers of your HTTP requests to ensure secure access to the services.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action creates images based on a text prompt, allowing for options like inpainting and refinement. This flexibility is particularly useful for generating interior design visuals, as you can specify various parameters such as seed, dimensions, and refinement methods.

Input

The input for this action is defined by a schema that includes several fields. Below is a detailed explanation of the necessary inputs along with an example.

  • Mask (optional): Input mask for inpaint mode (URI format). Black areas will be preserved, and white areas will be inpainted.
  • Seed (optional): Random seed for output generation. Leave blank for a randomized seed.
  • Image (optional): Input image URI for image-to-image or inpaint processing modes.
  • Width (optional): Width of the output image in pixels (default is 1024).
  • Height (optional): Height of the output image in pixels (default is 1024).
  • Prompt (required): Text prompt guiding the image generation.
  • Negative Prompt (optional): Text prompt indicating elements to avoid.
  • Number of Outputs (optional): Number of images to output (default is 1, maximum is 4).
  • Guidance Scale (optional): Scale for classifier-free guidance (default is 7.5).
  • Refine Style (optional): Style to refine the generated image (default is "no_refiner").
  • Apply Watermark (optional): Apply a watermark to the generated image (default is true).
  • Prompt Strength (optional): Strength of the prompt for image-to-image or inpainting (default is 0.8).
  • Number of Inference Steps (optional): Number of denoising steps to apply (default is 50).

Example Input:

{
  "image": "https://replicate.delivery/pbxt/KcjLG8lGt7w7cd8t8r0kivnE3i0jjEIr2djxcma2jqcuNodZ/CompressJPEG.online_512x512_image-2.jpg",
  "width": 512,
  "height": 512,
  "prompt": "Create a room in the cozy with the type room and the following furniture: chair, lamp",
  "loraScale": 1,
  "refineStyle": "base_image_refiner",
  "guidanceScale": 7.5,
  "schedulerType": "KarrasDPM",
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.85,
  "numberOfOutputs": 4,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}

Output

The output of the action typically includes an array of image URLs generated based on the input specifications. Here’s an example of what you might receive:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/29b59aa0-6b4a-47c1-a836-0a3dcaa30117/a01ef6bf-584c-410b-817f-0de009712f4c.png",
  "https://assets.cognitiveactions.com/invocations/29b59aa0-6b4a-47c1-a836-0a3dcaa30117/55e5c4ea-4d08-4e7c-906f-6030f9a349a6.png",
  "https://assets.cognitiveactions.com/invocations/29b59aa0-6b4a-47c1-a836-0a3dcaa30117/8bfe0f6b-500e-4968-84e4-1eb3c3c358a0.png",
  "https://assets.cognitiveactions.com/invocations/29b59aa0-6b4a-47c1-a836-0a3dcaa30117/a6549f6e-50d9-4daf-9e1b-fff01f39781d.png"
]

This output provides direct links to the generated images, which can be displayed or further processed in your application.

Conceptual Usage Example (Python)

Here’s a conceptual example of how to invoke the Generate Image with Inpainting 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 = "30965784-af32-4bac-8933-3e5c0d972ebe" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/KcjLG8lGt7w7cd8t8r0kivnE3i0jjEIr2djxcma2jqcuNodZ/CompressJPEG.online_512x512_image-2.jpg",
    "width": 512,
    "height": 512,
    "prompt": "Create a room in the cozy with the type room and the following furniture: chair, lamp",
    "loraScale": 1,
    "refineStyle": "base_image_refiner",
    "guidanceScale": 7.5,
    "schedulerType": "KarrasDPM",
    "applyWatermark": True,
    "negativePrompt": "",
    "promptStrength": 0.85,
    "numberOfOutputs": 4,
    "highNoiseFraction": 0.8,
    "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, you replace the placeholder API key and endpoint with your actual values. The payload is constructed based on the required input fields, and the action is executed by making a POST request to the hypothetical API endpoint. The response, if successful, will contain URLs to the generated images.

Conclusion

The Generate Image with Inpainting action from the kjw488/sdxl-demo-ai-interior API opens up exciting possibilities for developers looking to enhance their applications with rich, AI-generated visuals. By leveraging this action, you can bring your ideas to life with stunning images tailored to your specifications. Whether you're working on interior design, marketing, or any creative project, integrating these Cognitive Actions can significantly improve your workflow and output quality. Explore further, and let your creativity shine!

← Back to All Articles