image-generation

Create Stunning Custom Images with Leia's AI Capabilities

25 Apr 2025
Create Stunning Custom Images with Leia's AI Capabilities

In today's digital landscape, the ability to generate custom images on demand can vastly enhance your projects, whether for marketing, content creation, or personal use. The Leia service offers a powerful suite of Cognitive Actions designed specifically for image generation. With the ability to create customized images based on user-defined text prompts, Leia simplifies the creative process, allowing developers to produce high-quality visuals quickly and efficiently.

Imagine needing a unique image for a blog post, social media campaign, or even an art project. With Leia, you can generate images that meet specific criteria, including aspect ratios, sizes, and styles. This capability not only saves time but also opens up a realm of creative possibilities, allowing you to bring your ideas to life with just a few lines of code.

Prerequisites

To get started with Leia's image generation capabilities, you will need a valid Cognitive Actions API key and a basic understanding of making API calls.

Generate Customized Image

The "Generate Customized Image" action is at the heart of Leia's image generation service. This action allows you to create images from scratch based on a detailed text prompt. It supports image inpainting, speed optimization, and various output formats, making it an incredibly versatile tool for developers.

Purpose

This action addresses the need for quick and customizable image generation, enabling creatives to realize their visions without requiring extensive graphic design skills or resources.

Input Requirements

The input for this action is a JSON object that must include a "prompt" property, which serves as the basis for the generated image. Additionally, users can specify options such as:

  • mask: Image mask for inpainting mode.
  • seed: Random seed for reproducibility.
  • width and height: Dimensions of the image (only applicable in custom aspect ratio).
  • model: Choice of model for inference (e.g., "dev" or "schnell").
  • aspectRatio: Chosen aspect ratio for the image.
  • fastMode: Option for quicker predictions.
  • fileFormat: Desired output format (e.g., "webp", "jpg", "png").
  • inferenceSteps: Number of steps for generating the image.

Expected Output

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

[
  "https://assets.cognitiveactions.com/invocations/67c0dfe8-fd97-4b35-8427-2811959a79a5/9a9ddab8-c3aa-4c6e-9b93-a84687457c7e.jpg"
]

Use Cases for this Action

  1. Content Creation: Quickly generate custom images for blog posts, articles, or social media content that fit specific themes or concepts.
  2. Marketing Materials: Create visually appealing graphics for promotional campaigns that align with brand aesthetics.
  3. Art Projects: Use detailed prompts to generate unique artwork for personal or commercial projects.
  4. Game Development: Develop assets that meet specific narrative requirements, enhancing the storytelling aspect of games.
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 = "d64ce167-3780-44be-aba8-9144985d3098" # Action ID for: Generate Customized 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",
  "prompt": "A highly detailed digital painting of Leia Organa standing in a battle-ready stance, holding a red lightsaber ignited in her hand. She has an intense and determined expression, her brown eyes focused with unwavering resolve. Her hair is styled in intricate braids, reminiscent of her classic look but with a warrior's edge. She wears a dark, elegant outfit blending elements of her regal Alderaanian heritage with the practicality of a battle-hardened warrior—black and crimson robes with light armor plating. The background is a misty battlefield, illuminated by the eerie red glow of her saber, with sparks flying and remnants of a fallen enemy behind her. The scene is dramatic, with dynamic lighting emphasizing the contrast between the red blade and the cold environment.",
  "fastMode": false,
  "fileFormat": "jpg",
  "aspectRatio": "21:9",
  "imageQuality": 80,
  "mainLoraScale": 1,
  "inferenceSteps": 28,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "totalMegapixels": "1",
  "imageGuidanceScale": 3,
  "additionalLoraScale": 1
}

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

Leia's image generation capabilities empower developers to create stunning visuals tailored to their specific needs. By leveraging the "Generate Customized Image" action, you can streamline your creative workflows, produce high-quality images, and enhance your projects with unique visuals.

As you explore Leia's capabilities, consider experimenting with different prompts, settings, and outputs to fully harness the potential of this powerful tool. Whether you're building a marketing campaign or working on a creative project, Leia can help you bring your ideas to life effortlessly.

← Back to All Articles