Generate Stunning Miniature People Images with the iliketoasters Flux Cognitive Actions

24 Apr 2025
Generate Stunning Miniature People Images with the iliketoasters Flux Cognitive Actions

The iliketoasters/flux-miniature-people API provides developers with powerful Cognitive Actions designed to create visually striking images of miniature people. By utilizing the Flux LoRA model, these actions allow for the transformation of prompts into high-quality miniature representations in various scenes. This article will guide you through the capabilities of the primary action, its input requirements, expected outputs, and an illustrative usage example, enabling you to integrate it seamlessly into your applications.

Prerequisites

Before you can start using the Cognitive Actions, you will need an API key for the Cognitive Actions platform. This key is essential for authenticating your requests. Generally, you will pass the API key in the headers of your requests, allowing you to access the action functionalities securely.

Cognitive Actions Overview

Generate Miniature People Images

The Generate Miniature People Images action is designed to create images of miniature figures using specific prompts. This action reduces the typical plastic-like appearance of the figures, providing realistic miniature representations.

  • Category: Image Generation

Input

The input for this action requires a JSON object with several fields. The only required field is prompt, which specifies the scene description. Below are the core fields:

  • prompt: string (required)
    • Description: A detailed prompt for the generated image. For optimal results, include specific trigger words.
  • model: string (optional, default: "dev")
    • Description: The inference model to use; "dev" offers best performance with 28 inference steps, while "schnell" is optimized for speed.
  • aspectRatio: string (optional, default: "1:1")
    • Description: Set the aspect ratio for the generated image.
  • numberOfOutputs: integer (optional, default: 1)
    • Description: Number of output images to generate.
  • Additional fields include width, height, and various scaling options for LoRA weights, among others.

Here’s a sample input JSON structure:

{
  "model": "dev",
  "prompt": "over the shoulder shot, raw photo, a miniature man and woman sitting on a table, they are watching a movie on a smartphone propped up on its side",
  "aspectRatio": "1:1",
  "loraWeighting": 1,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "guidanceIntensity": 3.5,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 90,
  "inferenceStepCount": 28
}

Output

Upon successful execution, the action returns a JSON array containing URLs of the generated images. Here is an example output:

[
  "https://assets.cognitiveactions.com/invocations/1af5cfc8-2680-43fa-bed2-56c88c873afd/d1075c13-ce2a-44a6-ae36-fd1672980d82.webp"
]

The output typically includes the link to the generated image in the specified format.

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how you might invoke the Generate Miniature People Images 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 = "31519909-7fbd-4381-84ec-d6397a6cd169"  # Action ID for Generate Miniature People Images

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "over the shoulder shot, raw photo, a miniature man and woman sitting on a table, they are watching a movie on a smartphone propped up on its side",
    "aspectRatio": "1:1",
    "loraWeighting": 1,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "guidanceIntensity": 3.5,
    "imageOutputFormat": "webp",
    "imageOutputQuality": 90,
    "inferenceStepCount": 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:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • Use the appropriate action ID for the Generate Miniature People Images action.
  • The input payload is constructed to match the required schema.

Conclusion

The iliketoasters/flux-miniature-people Cognitive Action provides an innovative way to generate captivating miniature images. By understanding the input requirements and expected outputs, developers can easily integrate this functionality into their applications, opening up opportunities for creative visual content generation. As a next step, explore integrating additional parameters or experimenting with different prompts to achieve diverse visual styles. Happy coding!

← Back to All Articles