Create Unique Busytown Character Images with Zeke's Cognitive Actions

24 Apr 2025
Create Unique Busytown Character Images with Zeke's Cognitive Actions

In the realm of image generation, the Zeke/Busytown Cognitive Actions open up a world of creative possibilities for developers. With the ability to generate delightful images inspired by Richard Scarry's beloved Busytown, these pre-built actions allow for extensive customization through various parameters. This article will guide you on how to leverage these actions effectively in your applications.

Prerequisites

To get started with the Zeke/Busytown Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic understanding of JSON format for structuring API requests.
  • Familiarity with making HTTP requests from your preferred programming language.

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

Cognitive Actions Overview

Generate Busytown Character Images

The Generate Busytown Character Images action creates images based on a text prompt and various adjustable parameters. This action belongs to the image-generation category and allows developers to produce unique character images with a high degree of customization.

Input

To invoke this action, you need to structure your request as per the following schema:

{
  "mask": "string (uri)",
  "seed": "integer",
  "image": "string (uri)",
  "width": 1024,
  "height": 1024,
  "prompt": "string",
  "loraWeightSet": "string",
  "inferenceSteps": 50,
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "refinementSteps": "integer",
  "refinementStyle": "string",
  "schedulingMethod": "string",
  "highNoiseFraction": 0.8,
  "loraAdditiveScale": 0.6,
  "isWatermarkApplied": true,
  "guidanceScaleFactor": 7.5,
  "negativeImagePrompt": "string",
  "isSafetyCheckerDisabled": false
}

Example Input

{
  "width": 1024,
  "height": 1024,
  "prompt": "a warthog driving a pickle car in style of TOK",
  "inferenceSteps": 50,
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "refinementStyle": "no_refiner",
  "schedulingMethod": "K_EULER",
  "highNoiseFraction": 0.8,
  "loraAdditiveScale": 0.6,
  "isWatermarkApplied": true,
  "guidanceScaleFactor": 7.5,
  "negativeImagePrompt": ""
}

Output

When the action is successfully executed, it returns an array of image URLs, like the following example:

[
  "https://assets.cognitiveactions.com/invocations/beec76f6-228a-46c7-a66a-80b106956d6b/1b4a1d52-f9bc-4efe-a689-9cfa274197a3.png"
]

This output contains the generated image(s) based on your input parameters.

Conceptual Usage Example (Python)

Here’s a conceptual example of how to use the Generate Busytown Character Images action in 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 = "ef93f70a-522d-4b70-9699-56c9a45bb1ff"  # Action ID for Generate Busytown Character Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "a warthog driving a pickle car in style of TOK",
    "inferenceSteps": 50,
    "numberOfOutputs": 1,
    "promptIntensity": 0.8,
    "refinementStyle": "no_refiner",
    "schedulingMethod": "K_EULER",
    "highNoiseFraction": 0.8,
    "loraAdditiveScale": 0.6,
    "isWatermarkApplied": True,
    "guidanceScaleFactor": 7.5,
    "negativeImagePrompt": ""
}

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}
    )
    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 corresponds to the Generate Busytown Character Images action. The input payload is structured according to the specifications, ensuring all required fields are included.

Conclusion

The Zeke/Busytown Cognitive Actions provide a powerful and flexible way to generate creative images that resonate with the charm of Richard Scarry's Busytown. By integrating these actions into your applications, you can unlock a plethora of artistic possibilities. Consider experimenting with different prompts and parameters to see the variety of characters you can create! Happy coding!

← Back to All Articles