image-generation

Create Stunning Images Effortlessly with Luke Live

26 Apr 2025
Create Stunning Images Effortlessly with Luke Live

In a world where visual content is king, the ability to generate high-quality images quickly and efficiently is invaluable for developers and creators alike. Luke Live offers a powerful suite of Cognitive Actions that simplify the image generation process, allowing developers to focus on creativity rather than technical constraints. With options to fine-tune parameters such as aspect ratios, prompt strength, and output quality, you can produce stunning images tailored to your specific needs with ease.

Whether you're building a game, designing a website, or crafting marketing materials, Luke Live's image generation capabilities can enhance your projects significantly. Imagine generating unique visuals based on specific prompts, or creating variations of existing images for different contexts. This flexibility opens up endless possibilities for innovation and creativity.

Prerequisites

Before diving into the integration of Luke Live's Cognitive Actions, ensure you have your API key ready and a basic understanding of API calls. This foundational knowledge will help you make the most of the capabilities offered by this service.

Generate Enhanced Image

The Generate Enhanced Image action enables you to create high-quality images using either the 'dev' or 'schnell' models. This action is designed to address the need for rapid yet high-quality image generation. The 'dev' model is optimal for generating detailed images in approximately 28 inference steps, while the 'schnell' model offers a faster alternative, requiring only 4 steps, making it ideal for scenarios where speed is crucial.

Input Requirements

To use this action, you'll need to provide a prompt and can optionally include parameters such as the model type, aspect ratio, dimensions, and more. The essential input schema includes:

  • prompt (string): The textual description that guides the image generation.
  • model (string): Choose between 'dev' or 'schnell' for different generation speeds and qualities.
  • aspectRatio (string): Specify the desired aspect ratio for the image.
  • Additional parameters like width, height, guidanceScale, and outputQuality can further customize the output.

Expected Output

Upon successful execution, the action will return a URL linking to the generated image. For example:

  • https://assets.cognitiveactions.com/invocations/f622393e-266e-422f-ab2a-a926a4a59170/b070b3d5-062a-4848-b681-b0435ac737d5.jpg

Use Cases for this action

  • Game Development: Quickly generate character illustrations or backgrounds based on specific narratives or themes.
  • Marketing Campaigns: Create unique visuals that resonate with your target audience by generating images that align with your campaign's message.
  • Web Design: Produce tailored images for your website, ensuring that visual content is both engaging and relevant to your audience.
  • Content Creation: Streamline the process of producing visuals for blogs or social media, allowing for rapid updates and fresh content.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "b3afdf1b-b3ed-4167-b691-236a90aa11a9" # Action ID for: Generate Enhanced Image

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "model": "dev",
  "goFast": false,
  "prompt": "Luke skywalker standing tall in all black jedi robes",
  "aspectRatio": "21:9",
  "outputFormat": "jpg",
  "guidanceScale": 3,
  "mainLoraScale": 1,
  "outputQuality": 80,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "additionalLoraScale": 1,
  "numberOfInferenceSteps": 28
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Luke Live's image generation capabilities empower developers to create stunning visuals efficiently, enhancing various projects from games to marketing materials. The flexibility to fine-tune parameters allows for personalized and contextually relevant outputs, making it a valuable tool in a developer's arsenal. Ready to elevate your creative projects? Start integrating Luke Live today and unlock a world of visual possibilities!

← Back to All Articles