Enhance Your Images with Inpainting: A Guide to arjinroni/togg Cognitive Actions

22 Apr 2025
Enhance Your Images with Inpainting: A Guide to arjinroni/togg Cognitive Actions

In the world of image generation, the ability to create and enhance images with precision is invaluable. The arjinroni/togg spec offers powerful Cognitive Actions that harness advanced inpainting techniques, enabling developers to generate high-quality images tailored to specific needs. With customizable parameters for refinement style, guidance scale, and more, these pre-built actions simplify the integration of sophisticated image processing capabilities into your applications.

Prerequisites

To get started with the arjinroni/togg Cognitive Actions, you will need an API key for the Cognitive Actions platform. Authentication typically involves passing this API key in the request headers when making calls to the action endpoints. Ensure you set up your environment to handle HTTP requests, as you'll be interacting with the API programmatically.

Cognitive Actions Overview

Generate Enhanced Image with Inpainting

Description: This action generates and enhances images using inpainting techniques. It allows for customizable parameters such as refinement style, guidance scale, and image resolution. You can apply specific prompts to guide the image generation process, and it supports multiple scheduler models, along with options for watermarking and safety checks.

Category: Image Generation

Input

The following fields are required to construct the input for this action:

  • mask (string): URI for the input mask when using inpaint mode. Black areas are preserved, while white areas are inpainted.
  • seed (integer, optional): Integer seed for randomization. Leave blank to use a randomized seed.
  • image (string): URI of the input image for img2img or inpaint mode.
  • width (integer, default: 1024): Output image width in pixels.
  • height (integer, default: 1024): Output image height in pixels.
  • prompt (string, default: "An astronaut riding a rainbow unicorn"): Text prompt describing the desired attributes and style of the output image.
  • loraScale (number, default: 0.6, range: 0 to 1): Additive scale for LoRA, applicable on trained models.
  • outputCount (integer, default: 1, range: 1 to 4): Number of output images to generate.
  • refineStyle (string, default: "no_refiner"): The refinement strategy to apply.
  • guidanceScale (number, default: 7.5, range: 1 to 50): Classifier-free guidance scale for prompt adherence.
  • applyWatermark (boolean, default: true): If true, a watermark is applied to output images.
  • inferenceSteps (integer, default: 50, range: 1 to 500): Number of denoising steps during image generation.
  • negativePrompt (string, optional): Text prompt specifying undesirable attributes or styles for the output image.
  • promptStrength (number, default: 0.8, range: 0 to 1): Strength of the prompt when using img2img/inpaint.
  • refinementSteps (integer, optional): Number of steps to refine the image if using base_image_refiner.
  • schedulingMethod (string, default: "K_EULER"): Algorithm for scheduling the denoising process.
  • highNoiseFraction (number, default: 0.8, range: 0 to 1): Fraction of noise applied in the expert_ensemble_refiner process.
  • safetyCheckerDisabled (boolean, default: false): Disables the safety checker for generated images.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "product photography of TOK, lifestyle, in the streets of new york, skyscrapers in the background, night time, ultra high resolution, advertisement, luxury, professional lighting, speeding, dynamic, cinematic, 4k",
  "loraScale": 0.8,
  "outputCount": 3,
  "refineStyle": "no_refiner",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "inferenceSteps": 50,
  "promptStrength": 0.8,
  "schedulingMethod": "K_EULER",
  "highNoiseFraction": 0.8
}

Output

The action typically returns an array of URLs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e89281c8-1581-4b78-9151-b769fbc56108/851ff5e2-fc03-4260-b4d7-03e2a9c0a41e.png",
  "https://assets.cognitiveactions.com/invocations/e89281c8-1581-4b78-9151-b769fbc56108/97fb22f2-6a71-4cc3-9281-7460791e7082.png",
  "https://assets.cognitiveactions.com/invocations/e89281c8-1581-4b78-9151-b769fbc56108/c40d2beb-3239-4f88-819d-1faec7e3f898.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet demonstrating how to call the Generate Enhanced Image with Inpainting 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 = "89cd2e40-a81b-4bce-808e-3b39bf677075" # Action ID for Generate Enhanced Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "product photography of TOK, lifestyle, in the streets of new york, skyscrapers in the background, night time, ultra high resolution, advertisement, luxury, professional lighting, speeding, dynamic, cinematic, 4k",
    "loraScale": 0.8,
    "outputCount": 3,
    "refineStyle": "no_refiner",
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "inferenceSteps": 50,
    "promptStrength": 0.8,
    "schedulingMethod": "K_EULER",
    "highNoiseFraction": 0.8
}

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 and input payload are defined based on the requirements specified for the Generate Enhanced Image with Inpainting action.

Conclusion

The arjinroni/togg Cognitive Actions provide a robust solution for developers looking to integrate advanced image generation capabilities into their applications. By leveraging the Generate Enhanced Image with Inpainting action, you can create stunning visuals tailored to your specifications with ease. Explore the various parameters to fine-tune your image generation process, and consider how these actions can enhance your projects. Ready to get started? Dive into the integration and unleash your creativity!

← Back to All Articles