Create Stunning Images with the swk23/anakin Cognitive Actions

24 Apr 2025
Create Stunning Images with the swk23/anakin Cognitive Actions

In today's digital landscape, the demand for visually captivating content is ever-increasing. The swk23/anakin Cognitive Actions empower developers to generate custom images seamlessly through a powerful API integration. With the ability to specify various parameters such as prompts, dimensions, and output formats, these pre-built actions save time and enhance creativity. In this article, we will explore how to leverage the Generate Custom Image action to create stunning images tailored to your needs.

Prerequisites

To get started with the swk23/anakin Cognitive Actions, you will need:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic familiarity with making HTTP requests and handling JSON data in your preferred programming language.
  • A conceptual understanding of how to structure your API calls, including headers for authentication.

Authentication typically involves passing your API key in the request headers to ensure secure and authorized access to the Cognitive Actions.

Cognitive Actions Overview

Generate Custom Image

The Generate Custom Image action allows you to create a customized image based on a variety of input parameters. You can specify details like a mask URI for inpainting, a seed for random initialization, and other settings to fine-tune the output. This action falls under the category of image-generation.

Input

The input schema for this action requires several fields, with the prompt being mandatory. Below is the breakdown of the required and optional fields:

  • prompt (required): A string that defines what the image should depict (e.g., "ANI wearing jedi clothing sitting on a couch with a friend talking").
  • mask (optional): A URI for an image mask used in inpainting mode.
  • seed (optional): An integer seed for deterministic image generation.
  • image (optional): A URI of an input image for transformations.
  • width (optional): An integer specifying the image width (256 – 1440).
  • height (optional): An integer specifying the image height (256 – 1440).
  • goFast (optional): A boolean to enable faster predictions using a speed-optimized model.
  • aspectRatio (optional): An enum value selecting the aspect ratio (e.g., "1:1", "16:9", etc.).
  • numOutputs (optional): An integer specifying the number of images to generate (1 – 4).
  • outputFormat (optional): The desired output format of the image (e.g., "jpg", "png").
  • guidanceScale (optional): A number to adjust the guidance scale for the diffusion process.
  • outputQuality (optional): An integer defining the image output quality (0 – 100).

Example Input

Here's an example of how the input JSON payload might look:

{
  "goFast": false,
  "prompt": "ANI wearing jedi clothing sitting on a couch with a friend talking",
  "loraScale": 1,
  "numOutputs": 1,
  "aspectRatio": "21:9",
  "outputFormat": "jpg",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageResolution": "1",
  "numInferenceSteps": 28
}

Output

The action will return a URL linking to the generated image. For example, the output might look like:

[
  "https://assets.cognitiveactions.com/invocations/e755f825-2c03-4984-b1ef-64c74031426e/a92b0b09-4c51-4986-958a-d9de4762f540.jpg"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet illustrating how to call the Generate Custom Image 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 = "57b781d6-7c56-4e18-bd4d-a1de9f302a6f"  # Action ID for Generate Custom Image

# Construct the input payload based on the action's requirements
payload = {
    "goFast": false,
    "prompt": "ANI wearing jedi clothing sitting on a couch with a friend talking",
    "loraScale": 1,
    "numOutputs": 1,
    "aspectRatio": "21:9",
    "outputFormat": "jpg",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageResolution": "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 example, ensure to fill in your API key and observe how the input payload is structured based on the action's requirements. The endpoint URL and request structure are illustrative and should be adapted based on the actual API documentation.

Conclusion

The swk23/anakin Cognitive Actions simplify the process of generating highly customizable images, enabling developers to enhance their applications with visually appealing content. By utilizing the Generate Custom Image action, you can easily create unique visuals tailored to your specifications. Explore further possibilities by integrating these actions into your projects, and unleash your creativity!

← Back to All Articles