Generate Stunning Images with the juliusk24/jakob Cognitive Actions

24 Apr 2025
Generate Stunning Images with the juliusk24/jakob Cognitive Actions

In the rapidly evolving field of AI, the ability to generate high-quality images on demand can significantly enhance user experiences and creativity. The juliusk24/jakob specification provides powerful Cognitive Actions that allow developers to generate images with custom settings such as aspect ratio, resolution, and model type. With pre-built functionalities like inpainting and LoRA weight application, these actions can be integrated seamlessly into your applications, enabling you to create visually stunning content effortlessly.

Prerequisites

Before you start using the Cognitive Actions provided by the juliusk24/jakob specification, ensure you have the following:

  • An API key for the Cognitive Actions platform that can be passed in the headers of your requests.
  • Basic understanding of JSON and familiarity with making API calls.

Authentication typically involves including your API key in the request headers, allowing secure access to the available actions.

Cognitive Actions Overview

Generate Image with Custom Settings

This action generates high-quality images based on specified parameters such as aspect ratio, resolution, model type, and more. It supports advanced functionalities like inpainting and the application of LoRA weights, making it suitable for diverse creative tasks.

Input

The input schema for this action requires a prompt and allows for various optional parameters. Here’s a breakdown of the necessary fields:

  • prompt (string, required): The text prompt that guides the image generation.
  • image (string, optional): URI of the input image for image-to-image or inpainting mode.
  • aspectRatio (string, optional): Defines the aspect ratio of the output image (default is "1:1").
  • outputFormat (string, optional): Specifies the format for the output image (default is "webp").
  • numberOfOutputs (integer, optional): Number of images to generate per prompt (default is 1).
  • Additional parameters like seed, model, guidanceScale, etc., can be used to customize the output further.

Example Input

Here’s an example of the JSON payload you might send to this action:

{
  "image": "https://replicate.delivery/pbxt/Lt8KPYG1BIeIvxFryYBExEDPpqdafLvZcIfxqcKHVDV9GQK7/3f646442-8e3d-4db3-bcc4-a7d9461528da.png",
  "model": "dev",
  "prompt": "The camera captures the man in a close-up shot, focusing primarily on his upper body and face, revealing intricate details of his sharp, dark pinstripe suit and subtly patterned tie. His crisp white shirt peeks perfectly under the lapels, and a neatly folded pocket square adds a touch of refinement. The close framing emphasizes his composed expression, well-groomed hair, and confident gaze. The fine textures of the suit fabric are visible, illuminated by soft natural light from nearby windows. In the blurred background, hints of greenery and modern architecture subtly set the scene.",
  "aspectRatio": "1:1",
  "outputFormat": "png",
  "guidanceScale": 2.5,
  "loraIntensity": 1,
  "numberOfSteps": 28,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "additionalLoraScale": 1
}

Output

Upon successful execution, the action typically returns a URL to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/dcb6c2a4-59b4-4c3c-9dd8-44e40c12402c/f3aad6a3-0b85-4637-8a9e-24876f385947.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet to invoke the Generate Image with Custom Settings 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 = "b6b28560-3b4a-4960-a7e9-0b5642f5571e"  # Action ID for Generate Image with Custom Settings

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/Lt8KPYG1BIeIvxFryYBExEDPpqdafLvZcIfxqcKHVDV9GQK7/3f646442-8e3d-4db3-bcc4-a7d9461528da.png",
    "model": "dev",
    "prompt": "The camera captures the man in a close-up shot, ...",
    "aspectRatio": "1:1",
    "outputFormat": "png",
    "guidanceScale": 2.5,
    "loraIntensity": 1,
    "numberOfSteps": 28,
    "outputQuality": 90,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "additionalLoraScale": 1
}

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 Python snippet, you’ll replace the API key and endpoint with your actual credentials. The action ID and input payload are structured correctly to match the requirements of the Generate Image with Custom Settings action.

Conclusion

The juliusk24/jakob Cognitive Actions provide a powerful way to generate and customize images for various applications. By leveraging the flexibility of the input parameters and advanced features like LoRA weight application, developers can create unique and high-quality images tailored to specific needs. Start experimenting with these actions today to unlock the potential of AI-driven image generation in your projects!

← Back to All Articles