Generate Stunning Images with the marckohlbrugge/flux-wojak-v2 Cognitive Actions

23 Apr 2025
Generate Stunning Images with the marckohlbrugge/flux-wojak-v2 Cognitive Actions

In the evolving world of AI and image generation, the marckohlbrugge/flux-wojak-v2 offers developers a robust set of Cognitive Actions to create and manipulate images seamlessly. The primary action, Generate Custom Image Predictions, enables you to generate custom images through advanced techniques like image inpainting and image-to-image transformations. These pre-built actions streamline the process, allowing developers to focus on creativity rather than the complexities of image processing.

Prerequisites

Before diving into the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with JSON and basic HTTP request handling in your preferred programming language.

You will typically pass the API key in the headers of your requests, enabling secure access to the services.

Cognitive Actions Overview

Generate Custom Image Predictions

Purpose:
This action allows you to generate custom images using either image inpainting or image-to-image transformation modes. You can choose between two models: 'dev' for higher complexity or 'schnell' for faster results. Additionally, it supports multiple outputs, custom dimensions, and selectable image formats.

Input:
To invoke this action, you'll need to provide a JSON payload structured according to the specified input schema. Here’s a breakdown of the required and optional fields:

  • prompt (required): Text prompt for generating the image.
  • model (optional): Choose between 'dev' or 'schnell'. Default is 'dev'.
  • numOutputs (optional): Quantity of output images to generate (1 to 4).
  • aspectRatio (optional): Aspect ratio for the generated image. Default is '1:1'.
  • outputFormat (optional): Format for output images (WEBP, JPG, PNG).
  • guidanceScale (optional): Scale of guidance in the diffusion process. Default is 3.
  • outputQuality (optional): Quality level for output images (0 to 100).
  • numInferenceSteps (optional): Number of denoising steps (1 to 50).

Example Input:

{
  "model": "dev",
  "prompt": "black and white cartoon drawing of a man laughing hysterically, in the style of WOJEK. close up of his face with open mouth. with RED text \"HAHAHAHAHA\"",
  "loraScale": 1,
  "numOutputs": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 80,
  "numInferenceSteps": 28
}

Output:
When you execute this action, it typically returns a URL pointing to the generated images. Here’s an example of what the output might look like:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/741462ff-da4e-4451-a7e9-6d260bfcd39c/908eaad0-cf52-4f6d-b313-ca3cfbcf6efe.webp"
]

Conceptual Usage Example (Python): Here’s how you might call the Generate Custom Image Predictions 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 = "73ea2fff-9875-4bb5-a570-d8ac725bee60"  # Action ID for Generate Custom Image Predictions

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "black and white cartoon drawing of a man laughing hysterically, in the style of WOJEK. close up of his face with open mouth. with RED text \"HAHAHAHAHA\"",
    "loraScale": 1,
    "numOutputs": 1,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 80,
    "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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the Generate Custom Image Predictions action, and the payload matches the JSON structure outlined in the input schema.

Conclusion

The marckohlbrugge/flux-wojak-v2 Cognitive Actions empower developers to create and manipulate images effortlessly. With the Generate Custom Image Predictions action, you can leverage advanced techniques in image generation, opening up a world of creative possibilities. Whether you are building an application that requires unique visuals or just experimenting with AI image generation, these actions provide the tools you need to succeed.

Explore further by integrating these actions into your projects and see how they can enhance your applications!

← Back to All Articles