Unleashing Creativity: Integrate Image Generation with justswim/cats Cognitive Actions

23 Apr 2025
Unleashing Creativity: Integrate Image Generation with justswim/cats Cognitive Actions

In the world of digital creativity, generating unique images using artificial intelligence has become increasingly accessible. The justswim/cats Cognitive Actions provide a powerful API for developers looking to leverage image generation capabilities. One of the standout features is the ability to create images using an inpainting mode, allowing specific areas of an image to be repainted based on customized prompts. This article will guide you through the capabilities of the Generate Image with Inpainting action, detailing how to integrate it seamlessly into your applications.

Prerequisites

Before diving into the integration, you'll need to meet a few general requirements:

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with making HTTP requests in your programming language of choice.
  • Basic knowledge of JSON formatting, as the input and output structures will be in this format.

Authentication typically involves passing your API key in the headers of your requests, ensuring secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting

Description: This action allows you to create images using an inpainting mode where specific areas can be repainted based on input prompts. It also includes options for image refinement using various scheduler algorithms.

  • Category: Image Generation

Input

The input for this action requires a structured JSON object. Here are the key fields:

  • mask (string, required): URI of the input mask for the inpaint mode. Areas in black will be preserved, while those in white will be inpainted.
  • seed (integer, optional): Random seed for image generation. Leave empty for a random seed value.
  • image (string, required): URI of the input image for img2img or inpainting modes.
  • width (integer, optional): Width of the output image in pixels (default is 1024).
  • height (integer, optional): Height of the output image in pixels (default is 1024).
  • prompt (string, required): Descriptive input prompt for generating the image.
  • loraScale (number, optional): Scaling factor for LoRA model addition (default is 0.6).
  • applyWatermark (boolean, optional): Add a watermark to the generated image (default is true).
  • numberOfImages (integer, optional): Total number of images to generate (default is 1, max 4).
  • promptStrength (number, optional): Strength of the prompt when using inpainting (default is 0.8).
  • refinementStyle (string, optional): Choose the refinement style (default is "no_refiner").
  • schedulingMethod (string, optional): Choose the scheduling algorithm (default is "K_EULER").
  • numInferenceSteps (integer, optional): Total number of denoising steps during generation (default is 50).

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a video camera",
  "loraScale": 0.8,
  "guidanceScale": 7.5,
  "highNoiseFrac": 0.8,
  "applyWatermark": true,
  "negativePrompt": "background",
  "numberOfImages": 4,
  "promptStrength": 0.8,
  "refinementStyle": "no_refiner",
  "schedulingMethod": "K_EULER",
  "numInferenceSteps": 50
}

Output

Upon successful execution, the action returns an array of URIs pointing to the generated images. Here's what you can expect:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/55d05aac-2f53-430d-a3d1-ca5a00fb7baa/4318f032-d2e3-425a-ab35-63ceed198750.png",
  "https://assets.cognitiveactions.com/invocations/55d05aac-2f53-430d-a3d1-ca5a00fb7baa/88da7629-7d9a-4564-b72e-f52baa147840.png",
  "https://assets.cognitiveactions.com/invocations/55d05aac-2f53-430d-a3d1-ca5a00fb7baa/646a4d39-b01c-4d45-b753-6e27421ea855.png",
  "https://assets.cognitiveactions.com/invocations/55d05aac-2f53-430d-a3d1-ca5a00fb7baa/37fc3396-abf5-41dc-8120-2043386d89d1.png"
]

Conceptual Usage Example (Python)

Here’s how you might call 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 = "ba6d37da-f34e-4b0d-9faf-8c7ffdd960bc"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a video camera",
    "loraScale": 0.8,
    "guidanceScale": 7.5,
    "highNoiseFrac": 0.8,
    "applyWatermark": True,
    "negativePrompt": "background",
    "numberOfImages": 4,
    "promptStrength": 0.8,
    "refinementStyle": "no_refiner",
    "schedulingMethod": "K_EULER",
    "numInferenceSteps": 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 API key and endpoint with your own. The action ID corresponds to the Generate Image with Inpainting action. The input payload is structured to match the required schema, ensuring you supply the right parameters for successful image generation.

Conclusion

The justswim/cats Cognitive Actions provide developers with powerful tools to enhance their applications with creative image generation capabilities. By utilizing the Generate Image with Inpainting action, you can create unique visuals tailored to your specifications. Next steps could include exploring additional actions within the justswim/cats spec or experimenting with different input parameters to achieve various artistic styles. Embrace the power of AI and start generating captivating images today!

← Back to All Articles