Transform Your Images with Cognitive Actions: A Guide to jfals82/berno

24 Apr 2025
Transform Your Images with Cognitive Actions: A Guide to jfals82/berno

In the realm of image generation, the jfals82/berno Cognitive Actions provide powerful tools for developers looking to create stunning visuals through predictive inpainting and img2img transformations. With customizable parameters and options for refinement, these actions enable you to generate unique images tailored to your needs. Let’s dive into the capabilities of these Cognitive Actions and how to integrate them into your applications.

Prerequisites

Before you begin using the Cognitive Actions, ensure you have the following:

  • API Key: You'll need an API key to authenticate your requests to the Cognitive Actions platform. This key should be passed in the headers of your API requests.
  • Setup: Make sure you have access to the Cognitive Actions endpoint and the necessary libraries to make HTTP requests.

Cognitive Actions Overview

Generate Image with Inpainting and Img2Img

This action generates images by utilizing predictive inpainting and img2img transformations. You can define which areas of an image to preserve or alter using a mask, and customize various parameters for the output.

  • Category: image-generation

Input

The action requires a structured input, which can include the following fields:

  • mask (string): URI of the mask for inpainting mode. Black areas are preserved, while white areas are inpainted.
  • seed (integer, optional): Random seed for generating unique outputs. Leave null for a randomized seed.
  • image (string): URI of the input image for img2img or inpainting mode.
  • width (integer, default: 1024): Width of the output image in pixels.
  • height (integer, default: 1024): Height of the output image in pixels.
  • prompt (string, default: "An astronaut riding a rainbow unicorn"): Descriptive text prompt for image generation.
  • refine (string, default: "no_refiner"): Selects the refinement style to apply.
  • loraScale (number, default: 0.6): LoRA (Low-Rank Adaptation) additive scale factor.
  • scheduler (string, default: "K_EULER"): Algorithm for scheduling image generation.
  • guidanceScale (number, default: 7.5): Factor for classifier-free guidance scaling.
  • applyWatermark (boolean, default: true): Determines if a watermark should be applied.
  • negativePrompt (string): Descriptive prompt to specify undesired elements.
  • promptStrength (number, default: 0.8): Strength of the text prompt.
  • numberOfOutputs (integer, default: 1): Number of images to generate.
  • highNoiseFraction (number, default: 0.8): Fraction of noise applied.
  • numberOfInferenceSteps (integer, default: 50): Number of denoising steps.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "A picture of Berno, headshot, muscle, birthday hat, in the cab of a semi",
  "refine": "no_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns a JSON array containing the URLs of the generated images. Here's an example output:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/80dbb6e0-ce3c-4233-8110-9a6745021754/1f81bb6e-9fdb-48d0-8bd8-f98459af5738.png"
]

Conceptual Usage Example (Python)

To invoke this action, you can use the following Python code snippet:

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 = "a62ba6bc-1dea-4714-bc80-c59703e8202c"  # Action ID for Generate Image with Inpainting and Img2Img

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "A picture of Berno, headshot, muscle, birthday hat, in the cab of a semi",
    "refine": "no_refiner",
    "loraScale": 0.6,
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "negativePrompt": "",
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "highNoiseFraction": 0.8,
    "numberOfInferenceSteps": 50
}

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 input payload is structured according to the action requirements, and the action ID is specified accordingly. The response is handled to capture the generated image URLs.

Conclusion

The jfals82/berno Cognitive Actions provide a robust framework for developers to integrate advanced image generation capabilities into their applications. By leveraging the power of inpainting and img2img transformations, you can create unique and compelling visuals tailored to your specific needs. Explore these actions further to enhance your projects, and consider how they can add value to your applications. Happy coding!

← Back to All Articles