Generate Stunning Images with the treebridge83/luke-lora-2 Cognitive Actions

25 Apr 2025
Generate Stunning Images with the treebridge83/luke-lora-2 Cognitive Actions

In the realm of artificial intelligence and creative applications, the treebridge83/luke-lora-2 spec provides a powerful toolset for generating high-quality images. This spec features a single Cognitive Action designed to create images of Luke, utilizing a model specifically trained on related images. With adjustable parameters for customization, developers can harness this action to generate personalized images quickly and efficiently.

Prerequisites

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

  • API Access: An API key for the Cognitive Actions platform is required to authenticate your requests.
  • Basic Setup: Familiarity with making HTTP requests and handling JSON data in your development environment.

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

Cognitive Actions Overview

Generate Image of Luke

The Generate Image of Luke action creates a photo of Luke based on a text prompt and other customizable parameters. It is categorized under image-generation.

Input

The action requires a structured input defined by the following schema:

  • prompt (required): A descriptive text guiding the image generation.
  • mask (optional): URI of an image mask for inpainting mode.
  • seed (optional): Integer seed for reproducibility.
  • image (optional): URI of an input image for transformations.
  • width (optional): Pixel width of the generated image (256 to 1440).
  • height (optional): Pixel height of the generated image (256 to 1440).
  • goFast (optional): Boolean flag to enable faster predictions.
  • aspectRatio (optional, defaults to "1:1"): Aspect ratio of the generated image.
  • numOutputs (optional, defaults to 1): Number of images to generate (1 to 4).
  • outputFormat (optional, defaults to "webp"): File format of the output images.
  • guidanceScale (optional, defaults to 3): Scale factor for image realism.
  • outputQuality (optional, defaults to 80): Quality setting for output images.
  • extraLoraScale (optional, defaults to 1): Strength of applying extra LoRA.
  • inferenceModel (optional, defaults to "dev"): Model used for inference.
  • promptStrength (optional, defaults to 0.8): Strength of prompt application.
  • numInferenceSteps (optional, defaults to 28): Total denoising steps applied.

Example Input

Below is an example input JSON payload for this action:

{
  "prompt": "Mixxy as Wonder Woman in a dramatic pose, cinematic superhero film still, dynamic composition, intense lighting with dramatic shadows, vibrant color palette emphasizing red and blue, low-angle shot capturing heroic stance, lens flare, anamorphic widescreen format, high contrast, shallow depth of field, golden hour lighting, inspired by Zack Snyder's visual style, 4K resolution, IMAX quality, shot on Arri Alexa camera.",
  "loraScale": 1,
  "numOutputs": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "numInferenceSteps": 28
}

Output

The action typically returns a list of URLs pointing to the generated images. Here’s an example of a successful output:

[
  "https://assets.cognitiveactions.com/invocations/ac532c2f-7211-4664-aa14-fc7b5d32dc6e/ac2813af-eda3-48cd-b33c-674162926677.webp"
]

Conceptual Usage Example (Python)

Here’s how a developer might call the Generate Image of Luke 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 = "2b1672e4-138d-4d36-b208-6ff4f6d45ff2" # Action ID for Generate Image of Luke

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "Mixxy as Wonder Woman in a dramatic pose, cinematic superhero film still, dynamic composition, intense lighting with dramatic shadows, vibrant color palette emphasizing red and blue, low-angle shot capturing heroic stance, lens flare, anamorphic widescreen format, high contrast, shallow depth of field, golden hour lighting, inspired by Zack Snyder's visual style, 4K resolution, IMAX quality, shot on Arri Alexa camera.",
    "loraScale": 1,
    "numOutputs": 1,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "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 snippet, the action_id corresponds to the Generate Image of Luke action, and the input payload is structured according to the action's requirements. Remember that the endpoint URL and request structure are illustrative and may differ in actual implementation.

Conclusion

The Generate Image of Luke action from the treebridge83/luke-lora-2 spec provides developers with a robust solution for generating stunning images based on descriptive prompts. By leveraging the customizable parameters, you can create personalized outputs that align with your application's needs. Whether for creative projects, gaming, or marketing, integrating this action can significantly enhance the visual experience of your applications. Explore and experiment with the various input options to unlock the full potential of this powerful Cognitive Action!

← Back to All Articles