Enhance Image Generation with ControlNet Hough Cognitive Actions

21 Apr 2025
Enhance Image Generation with ControlNet Hough Cognitive Actions

Integrating advanced image processing capabilities into your applications can significantly elevate user experience and functionality. The jagilley/controlnet-hough Cognitive Actions offer developers a powerful way to modify images using the M-LSD line detection method, leveraging ControlNet for enhanced image generation. With pre-built actions, you can streamline the implementation of sophisticated features such as edge detection and image synthesis while maintaining control over various parameters.

Prerequisites

Before you begin, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • A basic understanding of how to make HTTP requests and work with JSON data structures.

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

Cognitive Actions Overview

Modify Image with M-LSD Line Detection

The Modify Image with M-LSD Line Detection action allows you to process and enhance images by utilizing the M-LSD line detection method integrated with Stable Diffusion. This action offers fine-tuned control through various adjustable parameters, enabling you to optimize the output based on your specific needs.

Input

The action requires the following fields in its input schema:

  • image (string): The URI of the input image. Must be a valid URL.
  • prompt (string): Text prompt to guide image generation.

Optional fields include:

  • seed (integer): Initializes the random number generator for reproducibility.
  • scale (number): Adjusts the influence of the prompt on the output (default: 9).
  • ddimSteps (integer): Number of DDIM steps for the generation process (default: 20).
  • negativePrompt (string): Text to avoid in the image generation (default includes various negative qualities).
  • valueThreshold (number): Threshold value for model application (default: 0.1).
  • imageResolution (string): Resolution of the output image (default: 512).
  • numberOfSamples (string): The number of samples to generate (default: 1).
  • additionalPrompt (string): Supplementary prompt for enhanced details (default: "best quality, extremely detailed").
  • distanceThreshold (number): Threshold for distance applicability (default: 0.1).
  • detectionResolution (integer): Resolution used during detection (default: 512).
  • estimatedTimeArrival (number): ETA for DDIM sampling process (default: 0).
Example Input
{
  "image": "https://replicate.delivery/pbxt/IJZOELWrncBcjdE1s5Ko8ou35ZOxjNxDqMf0BhoRUAtv76u4/room.png",
  "scale": 9,
  "prompt": "a cheerful modernist bedroom",
  "ddimSteps": 20,
  "negativePrompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "valueThreshold": 0.1,
  "imageResolution": "512",
  "numberOfSamples": "1",
  "additionalPrompt": "best quality, extremely detailed",
  "distanceThreshold": 0.1,
  "detectionResolution": 512
}

Output

The action typically returns an array of URIs pointing to the modified images created based on the provided input.

Example Output
[
  "https://assets.cognitiveactions.com/invocations/4df06421-88f9-4b30-8522-e7ffa83ccd9f/f910e839-727d-4005-b346-fae279ee7120.png",
  "https://assets.cognitiveactions.com/invocations/4df06421-88f9-4b30-8522-e7ffa83ccd9f/15edc7c1-aaf1-4383-8f92-8e54675e15e5.png"
]

Conceptual Usage Example (Python)

Here's how you might invoke this action using a conceptual Python code 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 = "71685110-404a-4f48-b1f0-e99ad035079c"  # Action ID for Modify Image with M-LSD Line Detection

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/IJZOELWrncBcjdE1s5Ko8ou35ZOxjNxDqMf0BhoRUAtv76u4/room.png",
    "scale": 9,
    "prompt": "a cheerful modernist bedroom",
    "ddimSteps": 20,
    "negativePrompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "valueThreshold": 0.1,
    "imageResolution": "512",
    "numberOfSamples": "1",
    "additionalPrompt": "best quality, extremely detailed",
    "distanceThreshold": 0.1,
    "detectionResolution": 512
}

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 example, replace "YOUR_COGNITIVE_ACTIONS_API_KEY" with your actual API key. The action ID should correspond to the action you are invoking, and the input payload should follow the structure outlined in the action's input schema.

Conclusion

The jagilley/controlnet-hough Cognitive Actions provide developers with powerful tools to modify and enhance images through advanced line detection and image generation techniques. By utilizing these actions, you can offer users sophisticated image processing capabilities while maintaining control over multiple parameters. Explore the possibilities of integrating these actions into your applications and unlock new levels of creativity and functionality.

← Back to All Articles