Transform Your Images: A Developer's Guide to the fofr/flux-beyond-horizon Cognitive Actions

25 Apr 2025
Transform Your Images: A Developer's Guide to the fofr/flux-beyond-horizon Cognitive Actions

In the rapidly evolving world of artificial intelligence, the ability to manipulate and generate images through advanced techniques like inpainting is a powerful tool for developers. The fofr/flux-beyond-horizon spec offers a set of Cognitive Actions that enable you to generate images using sophisticated algorithms. With features such as model selection for quality and speed, this guide will help you integrate these actions into your applications effortlessly.

Prerequisites

Before you start using the Cognitive Actions provided by the fofr/flux-beyond-horizon spec, ensure you have the following:

  • API Key: You’ll need to obtain an API key from the Cognitive Actions platform to authenticate your requests.
  • Basic Understanding of JSON: As the input and output for these actions are structured in JSON format, familiarity with JSON will be beneficial.

To authenticate your requests, you’ll typically include your API key in the request headers. This allows you to securely access the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create images by utilizing inpainting or transformation techniques. By providing an image URI and a mask, you can manipulate existing images or create entirely new ones. This action supports custom settings for quality, speed, and aspect ratio and offers optimized models for a balanced output.

Input

The input for this action is structured as follows:

{
  "prompt": "in the style of BYDHRZ, serene, contemplative, distant view, sci-fi",
  "model": "dev",
  "outputCount": 1,
  "mainLoraScale": 1,
  "denoisingSteps": 28,
  "imageAspectRatio": "16:9",
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "additionalLoraScale": 0.8,
  "diffusionGuidanceScale": 3.5
}

Required Fields:

  • prompt: A description or theme for the image generation. This is essential for guiding the model in creating the desired output.

Optional Fields:

  • mask: URI to an image mask for image inpainting.
  • seed: Integer for reproducible generation.
  • image: URI to an input image for transformation.
  • model: Choose between "dev" and "schnell".
  • width, height: Specify dimensions if using custom aspect ratio.
  • fastMode: Enable for quicker predictions.
  • outputCount: Number of images to generate (1-4).
  • imageAspectRatio: Choose the output aspect ratio.
  • imageOutputFormat: Specify the output format (webp, jpg, png).
  • imageOutputQuality: Set quality level (0-100).
  • additionalLora, mainLoraScale, additionalLoraScale: Control LoRA weights.
  • denoisingSteps: Number of inference steps.
  • safetyCheckerDisabled: Option to disable safety checks.

Output

The output of this action typically returns a list of URLs to the generated images. For example:

[
  "https://assets.cognitiveactions.com/invocations/4b803d0b-1d0d-4175-8468-32a284f08320/b86a4981-2bd1-4d75-9eec-6c3a9d2f1144.webp"
]

This URL points to the generated image based on the provided inputs.

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image with Inpainting action in 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 = "8918af8c-ab1d-49f5-b3ab-8cab053e897c" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "in the style of BYDHRZ, serene, contemplative, distant view, sci-fi",
    "model": "dev",
    "outputCount": 1,
    "mainLoraScale": 1,
    "denoisingSteps": 28,
    "imageAspectRatio": "16:9",
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "additionalLoraScale": 0.8,
    "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 example, replace "YOUR_COGNITIVE_ACTIONS_API_KEY" with your actual API key. The action_id corresponds to the Generate Image with Inpainting action, and the payload contains the structured input as per the action's requirements.

Conclusion

The fofr/flux-beyond-horizon Cognitive Actions provide powerful capabilities for image generation and manipulation through inpainting. By leveraging these actions, developers can create dynamic and visually engaging content tailored to their specific needs.

Explore potential use cases such as enhancing digital art, creating unique visuals for applications, or transforming existing images. Dive into the world of Cognitive Actions and unlock a new dimension of creativity in your applications!

← Back to All Articles