Create Stunning Images with candystalker/dame-taft Cognitive Actions

24 Apr 2025
Create Stunning Images with candystalker/dame-taft Cognitive Actions

In the world of AI and machine learning, the ability to generate custom images has opened up exciting new possibilities for developers and creatives alike. The candystalker/dame-taft Cognitive Actions provide a powerful way to create customized images through image-to-image transformations or inpainting modes. These pre-built actions come with a variety of parameters that allow you to control aspects like prompt strength, aspect ratio, output quality, and more. With the flexibility of using different models for speed and quality, integrating these actions into your applications can greatly enhance creativity and functionality.

Prerequisites

Before diving into using the Cognitive Actions, ensure that you have:

  • An API key for the Cognitive Actions platform.
  • Familiarity with JSON format, as the input and output will be structured in JSON.
  • Basic knowledge of Python for making API calls.

Authentication typically involves passing your API key in the request headers.

Cognitive Actions Overview

Generate Custom Image

This action allows you to create customized images using image-to-image transformation or inpainting mode. It supports various configurations to fine-tune your generated images.

Purpose: Generate a customized image based on the provided prompt and other parameters.

Category: Image Generation

Input

The input schema for this action is quite comprehensive, allowing for a variety of customizations. Here are the key fields:

  • prompt (required): The description for the generated image. E.g., "taft as a bespectacled cartoon lady holding a box of popcorn in one hand and smiling broadly."
  • aspectRatio (optional): Defines the image's aspect ratio. Default is "1:1".
  • width (optional): Specifies the width of the image (in pixels).
  • height (optional): Specifies the height of the image (in pixels).
  • numOutputs (optional): Number of output images to generate (1-4).
  • guidanceScale (optional): Scale for diffusion; recommended values include 2-3.5.
  • outputFormat (optional): The image file format (e.g., "png", "jpg").

Here’s an example input JSON payload:

{
  "goFast": false,
  "prompt": "taft as a bespectacled cartoon lady holding a box of popcorn in one hand and smiling broadly.",
  "loraScale": 1,
  "numOutputs": 4,
  "aspectRatio": "16:9",
  "outputFormat": "png",
  "guidanceScale": 3,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numInferenceSteps": 28
}

Output

The output of this action will typically be an array of URLs pointing to the generated images. Here's an example of what you might receive:

[
  "https://assets.cognitiveactions.com/invocations/0c32db35-6263-4b20-8ab4-5a5828fdacb7/eab6be8e-6fa0-43c3-b1f7-6fe03d30124a.png",
  "https://assets.cognitiveactions.com/invocations/0c32db35-6263-4b20-8ab4-5a5828fdacb7/c74d1546-bf7a-4cbe-a26f-d79190a51051.png",
  "https://assets.cognitiveactions.com/invocations/0c32db35-6263-4b20-8ab4-5a5828fdacb7/848f388b-a174-4a08-9943-962145e61e68.png",
  "https://assets.cognitiveactions.com/invocations/0c32db35-6263-4b20-8ab4-5a5828fdacb7/fd89dc4a-6f11-4aa9-a6ad-ce2f9c406e86.png"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how a developer might call the Cognitive Actions execution endpoint to generate a custom image:

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 = "7c5951c1-e00e-4a14-8696-5692dd223108"  # Action ID for Generate Custom Image

# Construct the input payload based on the action's requirements
payload = {
    "goFast": false,
    "prompt": "taft as a bespectacled cartoon lady holding a box of popcorn in one hand and smiling broadly.",
    "loraScale": 1,
    "numOutputs": 4,
    "aspectRatio": "16:9",
    "outputFormat": "png",
    "guidanceScale": 3,
    "outputQuality": 80,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageMegapixels": "1",
    "numInferenceSteps": 28
}

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 will replace the placeholders with your actual API key and endpoint. The action ID and input payload are structured according to the requirements of the Generate Custom Image action.

Conclusion

The candystalker/dame-taft Cognitive Actions provide a versatile way to generate custom images tailored to your application's needs. By leveraging the various parameters available, you can create stunning visuals that enhance user engagement. Whether you’re building an art app, a marketing tool, or simply exploring creative possibilities, these actions are a fantastic asset to your development toolkit. Start experimenting with image generation today and unlock new creative potentials!

← Back to All Articles