Streamline Image Generation with the schzerflori/brunopaul_flux Cognitive Actions

24 Apr 2025
Streamline Image Generation with the schzerflori/brunopaul_flux Cognitive Actions

In the realm of image synthesis and manipulation, the scherzerflori/brunopaul_flux API offers developers a powerful Cognitive Action designed for generating and inpainting images. This action allows for extensive customization, enabling you to create stunning visuals tailored to your specifications. With features like model selection, adjustable prompt strength, and various output formats, this API streamlines the image generation process, making it accessible and efficient for developers.

Prerequisites

To get started with the scherzerflori/brunopaul_flux Cognitive Actions, you'll need the following:

  • An API key for the Cognitive Actions platform, which will be used for authentication.
  • Basic knowledge of JSON and how to interact with RESTful APIs.

Authentication typically involves passing your API key in the request headers for authorization.

Cognitive Actions Overview

Generate Image with Inpainting and Model Selection

This action enables the creation of images through image-to-image transformation and inpainting. You can customize various parameters such as dimensions, model type, and prompt strength, allowing for a tailored generation experience.

Input

The input for this action follows the CompositeRequest schema, which requires a prompt and allows for a variety of optional fields:

{
  "prompt": "A vintage dark black and white illustration from 1900 in the style of BRUNOPAUL of a 21 years old poor farmer with a mustache and a hat staring at a strange statue of a saint inside a tiny dark chapel in Bavaria",
  "model": "dev",
  "megapixels": "1",
  "aspectRatio": "1:1",
  "guidanceScale": 3,
  "mainLoraScale": 1,
  "enableFastMode": false,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "additionalLoraScale": 1,
  "numberOfInferenceSteps": 28
}
  • Required Field:
    • prompt: Describes the content of the image to be generated.
  • Optional Fields:
    • model: Specifies which model to use for generation (e.g., "dev" or "schnell").
    • megapixels: Approximate megapixels for the generated image.
    • aspectRatio: Defines the aspect ratio (e.g., "1:1", "16:9", "custom").
    • guidanceScale: Influences adherence to the prompt.
    • mainLoraScale, additionalLoraScale: Adjusts the intensity of LoRA applications.
    • enableFastMode: Activates faster generation.
    • promptStrength: Adjusts the influence of the prompt on the output.
    • numberOfOutputs: Specifies how many images to generate.
    • imageOutputFormat: Defines the file format for the output image.
    • imageOutputQuality: Sets the quality of the output image.
    • numberOfInferenceSteps: Determines the number of steps in the denoising process.

Output

The output of this action is a URL to the generated image. Here’s an example of what the output might look like:

[
  "https://assets.cognitiveactions.com/invocations/d389fd95-ad2c-4616-b64e-22faca5f674c/253dfd0a-b696-4a2a-8b31-ab32a8674dd6.webp"
]

Conceptual Usage Example (Python)

Here's how you might call this action using a conceptual Python script:

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 = "bf26bba7-0c27-481d-b8d0-de8cf40e1268"  # Action ID for Generate Image with Inpainting and Model Selection

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "A vintage dark black and white illustration from 1900 in the style of BRUNOPAUL of a 21 years old poor farmer with a mustache and a hat staring at a strange statue of a saint inside a tiny dark chapel in Bavaria",
    "model": "dev",
    "megapixels": "1",
    "aspectRatio": "1:1",
    "guidanceScale": 3,
    "mainLoraScale": 1,
    "enableFastMode": False,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "additionalLoraScale": 1,
    "numberOfInferenceSteps": 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 example, you’ll need to replace the placeholder API key and endpoint with your actual credentials. The payload is structured to match the required input schema, ensuring that you successfully generate an image.

Conclusion

The scherzerflori/brunopaul_flux Cognitive Actions provide a comprehensive solution for image generation, enabling developers to craft unique visuals with a high degree of control. By leveraging the power of customizable parameters and model selection, you can create images that meet specific needs and artistic visions. As you explore this action, consider how it can enhance your applications and open up new creative possibilities. Happy coding!

← Back to All Articles