Unlocking Image Generation with the BeyondSuperbia/Flux Cognitive Actions

23 Apr 2025
Unlocking Image Generation with the BeyondSuperbia/Flux Cognitive Actions

In the ever-evolving landscape of artificial intelligence, image generation stands out as a fascinating application area. The BeyondSuperbia/Flux Cognitive Actions provide a powerful set of tools for developers looking to generate detailed images based on text prompts, perform inpainting, and utilize image-to-image transformations. With options for custom dimensions, multiple output formats, and fast generation modes, these actions allow for high-quality image creation that can enhance applications across various industries.

Prerequisites

Before diving into the integration of the Cognitive Actions, you will need:

  • An API key for the BeyondSuperbia Cognitive Actions platform to authenticate your requests.
  • Basic understanding of JSON structure, as input and output data will be in this format.

Authentication typically involves including the API key in the request headers, enabling you to access the available actions seamlessly.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create intricate images based on text prompts, offering options for image transformation and inpainting. This action supports multiple configurations to tailor the output to your needs.

Input

The input schema for this action requires a JSON object with various fields, the most crucial being the prompt. Here's a breakdown of the input fields:

  • prompt (required): A string that describes the image to be generated.
  • model (optional): Selects the inference model, either 'dev' or 'schnell' (default: 'dev').
  • image (optional): Input image for inpainting or transformation.
  • mask (optional): Image mask for inpainting mode.
  • width (optional): Desired width of the generated image (256 to 1440).
  • height (optional): Desired height of the generated image (256 to 1440).
  • goFast (optional): Boolean to enable faster predictions.
  • imageFormat (optional): Output format (webp, jpg, png; default: webp).
  • outputCount (optional): Number of images to generate (1 to 4; default: 1).
  • imageQuality (optional): Quality of output images (0 to 100; default: 80).
  • loraStrength (optional): Strength of the main LoRA application (default: 1).
  • imageResolution (optional): Approximate resolution in megapixels (default: 1).
  • promptIntensity (optional): Strength of the prompt for img2img (default: 0.8).
  • imageAspectRatio (optional): Desired aspect ratio for the image.
  • diffusionGuidance (optional): Guidance scale for the diffusion process (default: 3).
  • inferenceStepCount (optional): Number of denoising steps (default: 28).
  • additionalLoraStrength (optional): Strength for secondary LoRA application (default: 1).
  • isSafetyCheckerDisabled (optional): Option to disable the safety checker (default: false).

Here’s an example of the input JSON payload:

{
  "model": "dev",
  "goFast": false,
  "prompt": "Ultra-detailed close-up of a rugged Ford Ranger Wildtrak tyre rolling on a pristine tar road, highlighting the deep treads and suspension components, cinematic lighting, realistic textures, motion blur on the wheel, high realism",
  "imageFormat": "webp",
  "outputCount": 1,
  "imageQuality": 80,
  "loraStrength": 1,
  "imageResolution": "1",
  "promptIntensity": 0.8,
  "imageAspectRatio": "16:9",
  "diffusionGuidance": 3,
  "inferenceStepCount": 28,
  "additionalLoraStrength": 1
}

Output

Upon successful execution, the action returns an array of URLs pointing to the generated images. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/6a076c0b-2b4e-4e50-bab3-455c336bfdb8/69ffb8de-1339-4024-86ed-98cc6388b15c.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how a developer might call this action using a hypothetical Cognitive Actions execution endpoint:

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 = "292864b1-8509-4f33-a4f0-033b8ac54346"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "Ultra-detailed close-up of a rugged Ford Ranger Wildtrak tyre rolling on a pristine tar road, highlighting the deep treads and suspension components, cinematic lighting, realistic textures, motion blur on the wheel, high realism",
    "imageFormat": "webp",
    "outputCount": 1,
    "imageQuality": 80,
    "loraStrength": 1,
    "imageResolution": "1",
    "promptIntensity": 0.8,
    "imageAspectRatio": "16:9",
    "diffusionGuidance": 3,
    "inferenceStepCount": 28,
    "additionalLoraStrength": 1
}

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 snippet:

  • The action_id corresponds to the Generate Image with Inpainting action.
  • The payload is structured according to the required input schema.
  • The response is handled gracefully, printing the resulting image URLs or any error messages.

Conclusion

The BeyondSuperbia/Flux Cognitive Actions provide a robust set of capabilities for generating images and performing complex transformations. By leveraging these actions, developers can automate image creation processes, enhance user experiences, and explore creative applications in various domains. With the provided examples and Python snippets, you are well-equipped to integrate these powerful Cognitive Actions into your applications. Happy coding!

← Back to All Articles