Create Stunning Lomography-Style Photos with levelsio/lomography Cognitive Actions

23 Apr 2025
Create Stunning Lomography-Style Photos with levelsio/lomography Cognitive Actions

In the world of photography, Lomography captures the essence of spontaneity and creativity through its unique aesthetic. The levelsio/lomography API offers developers the ability to generate images in the distinctive style of Lomography cameras. This API comes equipped with customizable parameters that allow you to control aspects such as image dimensions, quality, and artistic effects, enabling a rich and engaging image generation experience.

Prerequisites

To get started with the levelsio/lomography Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be used for authentication.
  • Basic knowledge of JSON structure for constructing requests.

Authentication typically involves passing your API key in the request headers which will allow you to access the API securely.

Cognitive Actions Overview

Generate Lomography Style Photos

Purpose

This action allows you to create images in the iconic Lomography style, leveraging customizable parameters such as image dimensions, output quality, and prompt strength. You can choose between detailed or quick outputs, making it versatile for various applications.

Input

The input schema for this action requires a prompt and offers many optional parameters to fine-tune the image generation. Here’s a breakdown:

  • Required:
    • prompt (string): Describes the image to be generated. Example: "Photo of blonde man at the beach in the style of TOK lomography fisheye".
  • Optional:
    • mask (string): URI for image mask in inpainting mode.
    • seed (integer): Random seed for reproducibility.
    • image (string): URI of an input image for inpainting.
    • model (string): Selects the inference model ('dev' or 'schnell').
    • width (integer): Width of the output image.
    • height (integer): Height of the output image.
    • fastMode (boolean): Enables faster predictions.
    • aspectRatio (string): Defines the aspect ratio.
    • outputFormat (string): Desired format of the output images.
    • And several other parameters related to LoRA weights, quality, and inference steps.

Example Input:

{
  "model": "dev",
  "prompt": "Photo of blonde man at the beach in the style of TOK lomography fisheye",
  "aspectRatio": "16:9",
  "outputFormat": "webp",
  "mainLoraScale": 1,
  "numberOfOutputs": 1,
  "imageOutputQuality": 80,
  "inferenceStepsCount": 28,
  "diffusionGuidanceScale": 3.5
}

Output

The action returns a URL pointing to the generated image. Here’s an example of what the output may look like:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/56bf05e8-79a9-43b6-83ec-e84f1a2614c8/be7d425e-381f-4f79-9198-18bb6d514ba0.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet to illustrate how you might call this 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 = "0e3ad377-5613-403b-9ee1-39660ec0cf92" # Action ID for Generate Lomography Style Photos

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "Photo of blonde man at the beach in the style of TOK lomography fisheye",
    "aspectRatio": "16:9",
    "outputFormat": "webp",
    "mainLoraScale": 1,
    "numberOfOutputs": 1,
    "imageOutputQuality": 80,
    "inferenceStepsCount": 28,
    "diffusionGuidanceScale": 3.5
}

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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID for generating Lomography-style photos is specified, and the input JSON payload is constructed based on the action's requirements.

Conclusion

The levelsio/lomography Cognitive Actions provide powerful tools for developers to generate stunning Lomography-style images with customizable options. By utilizing these actions, you can enhance your applications with visually appealing content, tailored to your users' needs. Explore the possibilities of creative image generation and integrate these actions into your projects to elevate your application's visual storytelling.

← Back to All Articles