Generate Stunning Images with the jakubluczywo/model-jakuba Cognitive Actions

21 Apr 2025
Generate Stunning Images with the jakubluczywo/model-jakuba Cognitive Actions

In the realm of image generation, the jakubluczywo/model-jakuba API offers powerful Cognitive Actions that harness advanced inpainting techniques to produce high-quality visuals. With options for customizing dimensions, output formats, and detail enhancements, developers can seamlessly integrate these actions into their applications to generate stunning images tailored to their specific needs.

Prerequisites

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

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with making API requests, particularly using JSON for input and output.
  • Basic knowledge of Python to implement the conceptual examples provided.

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

Cognitive Actions Overview

Generate Image with Enhanced Inpainting

Description:
This action generates high-quality images using inpainting techniques. It allows customization of dimensions, output format, and detail enhancement through the 'schnell' or 'dev' models—optimized for either speed or precision.

Category: Image Generation

Input

The input for this action is structured as follows:

  • prompt (required): A descriptive prompt for the image to be generated.
  • mask (optional): An image mask for inpainting. If provided, other size parameters will be ignored.
  • seed (optional): A random seed for reproducibility.
  • image (optional): An input image for inpainting. If provided, size parameters will be ignored.
  • width (optional): Desired width of the generated image (256-1440).
  • height (optional): Desired height of the generated image (256-1440).
  • imageFormat (optional): Format for the output image (webp, jpg, png).
  • outputCount (optional): Number of images to generate (1-4).
  • imageQuality (optional): Quality of output images (0-100).
  • inferenceModel (optional): The model to run inference with (dev, schnell).
  • imageAspectRatio (optional): Aspect ratio for the generated image.
  • additional parameters for fine-tuning such as prompt intensity, inference steps, and more.

Example Input:

{
  "prompt": "JTL, Realistic photo of a young man with a thick, well-groomed beard and a stylish slicked-back hairstyle, highly detailed, photorealistic, sharp focus, natural skin tone. Man in front position",
  "imageFormat": "webp",
  "outputCount": 3,
  "imageQuality": 80,
  "mainLoraScale": 1,
  "inferenceModel": "dev",
  "imageMegapixels": "1",
  "promptIntensity": 1,
  "imageAspectRatio": "1:1",
  "accelerateInference": false,
  "additionalLoraScale": 1,
  "inferenceStepsCount": 50,
  "diffusionGuidanceScale": 2
}

Output

The action typically returns an array of URLs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/68608a33-5fe2-4b1f-8deb-93e44664d25f/64bda20a-93ca-4457-a0dd-62555e2648f6.webp",
  "https://assets.cognitiveactions.com/invocations/68608a33-5fe2-4b1f-8deb-93e44664d25f/d3bc2737-1ec1-49ab-9f47-e55e5ad3a07e.webp",
  "https://assets.cognitiveactions.com/invocations/68608a33-5fe2-4b1f-8deb-93e44664d25f/5be1b7af-d74b-48c2-9747-ec199fde80ab.webp"
]

Conceptual Usage Example (Python)

Here’s how a developer might structure a request to invoke this 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 = "276c2387-2cae-4697-af6d-8f3b83d851fe"  # Action ID for Generate Image with Enhanced Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "JTL, Realistic photo of a young man with a thick, well-groomed beard and a stylish slicked-back hairstyle, highly detailed, photorealistic, sharp focus, natural skin tone. Man in front position",
    "imageFormat": "webp",
    "outputCount": 3,
    "imageQuality": 80,
    "mainLoraScale": 1,
    "inferenceModel": "dev",
    "imageMegapixels": "1",
    "promptIntensity": 1,
    "imageAspectRatio": "1:1",
    "accelerateInference": False,
    "additionalLoraScale": 1,
    "inferenceStepsCount": 50,
    "diffusionGuidanceScale": 2
}

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 Python code snippet, replace the COGNITIVE_ACTIONS_API_KEY with your API key. The payload dictionary is structured according to the input schema for the action. The URL and the request structure are illustrative and may vary based on your actual implementation.

Conclusion

The jakubluczywo/model-jakuba Cognitive Actions provide powerful tools for developers looking to create high-quality images with ease. By leveraging the flexibility and customization options available through these actions, you can integrate stunning image generation capabilities into your applications. Consider experimenting with various input parameters to discover the best configurations for your specific use cases!

← Back to All Articles