Mastering Image Generation with the swk23/cw-obiwan-live Cognitive Actions

24 Apr 2025
Mastering Image Generation with the swk23/cw-obiwan-live Cognitive Actions

In the realm of creative applications, the swk23/cw-obiwan-live Cognitive Actions provide developers with powerful tools for image generation. With a focus on fine-tuning capabilities, these actions facilitate the creation of stunning visuals that can be customized through various parameters, making them ideal for artistic projects, game design, or any application requiring dynamic imagery.

Prerequisites

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

  • API Key: You will need an API key to access the Cognitive Actions platform.
  • Setup: Familiarize yourself with how to send requests to the API endpoint, typically involving setting the API key in the request headers.

Authentication Concept: Generally, you will pass your API key via headers in your requests, allowing you to securely access the available actions.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create images using advanced models while providing options for inpainting, aspect ratio adjustments, and prompt-guided generation. This flexibility enables developers to fine-tune the images generated according to their specific requirements.

Input

The input for this action is structured as follows:

  • Required Fields:
    • prompt: A descriptive text guiding the generation of the image.
  • Optional Fields:
    • mask: URI of the image mask for inpainting.
    • seed: Integer for consistent image generation.
    • image: URI for image-to-image or inpainting mode.
    • width: Width of the generated image (if aspect ratio is custom).
    • height: Height of the generated image (if aspect ratio is custom).
    • modelType: Designates the model type for inference (default: dev).
    • imageFormat: File format for output images (default: webp).
    • loraWeights: Load LoRA weights from supported sources.
    • imageQuality: Quality level for saved images (default: 80).
    • inferenceSteps: Number of denoising steps (default: 28).
    • numberOfOutputs: Number of output images to generate (default: 1).
    • Other parameters control aspects like promptIntensity, guidanceIntensity, and more.

Example Input:

{
  "prompt": "**Prompt:**  \nA close-up cinematic shot of Obi-Wan Kenobi standing in a quiet chamber of the Jedi Temple during sunset, wearing his white Clone Wars-era Jedi armor. The golden-orange sunlight streams through tall arched windows, casting a warm glow across the room and illuminating the polished surface of his chestplate. Subtle scratches and scuffs on the armor hint at recent battles, while his face remains calm and introspective. The light highlights the contours of his beard and the determined look in his eyes. Behind him, the blurred architecture of the Jedi Temple—stone columns and sacred carvings—adds to the solemn, reflective mood of this quiet moment between wars.",
  "modelType": "dev",
  "imageFormat": "jpg",
  "imageQuality": 80,
  "loraIntensity": 1,
  "enableFastMode": false,
  "inferenceSteps": 28,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "imageAspectRatio": "21:9",
  "guidanceIntensity": 3,
  "additionalLoraIntensity": 1
}

Output

Upon successful execution, the action typically returns a URL leading to the generated image. The output is structured as follows:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/01611f38-9522-4a9f-9cd4-71cc86d0156e/0b106d54-a86e-49a7-921f-12bd7fc06409.jpg"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to invoke the Generate Image with Inpainting 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 = "99895c01-d523-4062-86f0-b27ca311876a" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "**Prompt:**  \nA close-up cinematic shot of Obi-Wan Kenobi standing in a quiet chamber of the Jedi Temple during sunset, wearing his white Clone Wars-era Jedi armor. The golden-orange sunlight streams through tall arched windows, casting a warm glow across the room and illuminating the polished surface of his chestplate. Subtle scratches and scuffs on the armor hint at recent battles, while his face remains calm and introspective. The light highlights the contours of his beard and the determined look in his eyes. Behind him, the blurred architecture of the Jedi Temple—stone columns and sacred carvings—adds to the solemn, reflective mood of this quiet moment between wars.",
    "modelType": "dev",
    "imageFormat": "jpg",
    "imageQuality": 80,
    "loraIntensity": 1,
    "enableFastMode": False,
    "inferenceSteps": 28,
    "imageMegapixels": "1",
    "numberOfOutputs": 1,
    "promptIntensity": 0.8,
    "imageAspectRatio": "21:9",
    "guidanceIntensity": 3,
    "additionalLoraIntensity": 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} # 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 snippet, replace the hypothetical API key and endpoint with your actual credentials. The input JSON is structured to meet the action requirements, focusing on specifying the prompt and other parameters accurately.

Conclusion

The swk23/cw-obiwan-live Cognitive Actions offer an exciting opportunity for developers to harness advanced image generation capabilities. By utilizing the Generate Image with Inpainting action, you can create stunning visuals that not only meet your application's needs but also enhance user engagement. As you explore these actions, consider experimenting with various parameters to achieve the best results for your specific use cases. Happy coding!

← Back to All Articles