Expand Your Creativity: Outpainting Images with the ControlNet++ Cognitive Action

25 Apr 2025
Expand Your Creativity: Outpainting Images with the ControlNet++ Cognitive Action

In the realm of image generation, the emaph/outpaint-controlnet-union API offers powerful Cognitive Actions that allow developers to enhance and expand their creative projects. One of the standout features is the ability to perform outpainting using ControlNet++, which brings advanced image processing capabilities to your applications. This action not only expands images beyond their original borders but also utilizes cutting-edge techniques to ensure high-quality, diverse outputs. Let’s explore how you can integrate this Cognitive Action into your application.

Prerequisites

Before diving into the implementation, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be used for authentication.
  • Basic knowledge of making HTTP requests and handling JSON data in your applications.

Authentication typically involves passing your API key in the headers of your request to gain access to the Cognitive Actions.

Cognitive Actions Overview

Outpaint Image Using ControlNet++

The Outpaint Image Using ControlNet++ action allows you to expand an image beyond its original borders, leveraging advanced techniques for high-resolution output. It is particularly useful for applications requiring creative expansions of existing images.

Input

The input schema for this action requires a JSON object with the following fields:

  • seed (integer, optional): Sets a seed for reproducibility. Default is a random seed.
  • prompt (string, optional): A text prompt to guide image generation. Default is an empty string.
  • imageUri (string, required): The URI of the image to expand in the outpaint process.
  • outpaintTop (integer, optional): Specifies the number of pixels to expand at the top. Default is 150 pixels.
  • outpaintLeft (integer, optional): Specifies the number of pixels to expand on the left side. Default is 150 pixels.
  • outpaintRight (integer, optional): Specifies the number of pixels to expand on the right side. Default is 150 pixels.
  • outpaintBottom (integer, optional): Specifies the number of pixels to expand at the bottom. Default is 150 pixels.
  • outputFormat (string, optional): Specifies the format of the output images (webp, jpg, png). Default is webp.
  • outputQuality (integer, optional): Quality of the output images, from 0 to 100. Default is 80.
  • guidanceScale (number, optional): Influences image generation with a scale from 0 to 20. Default is 4.
  • inferenceSteps (integer, optional): Denotes the number of inference steps for image generation, ranging from 1 to 50. Default is 20.
  • negativePrompt (string, optional): Text to specify elements not to include in the generated image. Default is "ugly".

Here’s an example input payload for the action:

{
  "prompt": "ice dragon, wings wide open",
  "imageUri": "https://i.postimg.cc/vmY5BZP3/2024-04-16-21-30-59-9956.png",
  "outpaintTop": 0,
  "outpaintLeft": 400,
  "outputFormat": "webp",
  "outpaintRight": 400,
  "outputQuality": 80,
  "negativePrompt": "ugly",
  "outpaintBottom": 0
}

Output

Upon successful execution, the action returns a JSON array containing the URI of the expanded image. Here’s an example of the expected output:

[
  "https://assets.cognitiveactions.com/invocations/b2550467-ab1b-46a2-9d0c-51f3235b0e87/fc02f0b4-938d-4751-9594-abb113c0d089.webp"
]

This output provides the location of the newly generated image, which you can utilize in your application.

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet demonstrating how to call the Outpaint Image Using ControlNet++ action:

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 = "daaa0e4b-1e99-4dc0-811b-9fea703b67e3"  # Action ID for Outpaint Image Using ControlNet++

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "ice dragon, wings wide open",
    "imageUri": "https://i.postimg.cc/vmY5BZP3/2024-04-16-21-30-59-9956.png",
    "outpaintTop": 0,
    "outpaintLeft": 400,
    "outputFormat": "webp",
    "outpaintRight": 400,
    "outputQuality": 80,
    "negativePrompt": "ugly",
    "outpaintBottom": 0
}

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 and ensure the endpoint URL is accurate. The payload is structured according to the input schema, and the response is handled gracefully.

Conclusion

The Outpaint Image Using ControlNet++ action opens up a world of possibilities for creative image manipulation. By integrating this Cognitive Action into your applications, you can effortlessly expand images and enhance user experiences. Whether you're working on an art project or a commercial application, leveraging this technology can significantly elevate your work.

Explore the potential of image outpainting today and consider how you might apply these capabilities to your next project!

← Back to All Articles