Enhancing Image Generation with the automioai/carlosescobar93 Cognitive Actions

24 Apr 2025
Enhancing Image Generation with the automioai/carlosescobar93 Cognitive Actions

In the realm of artificial intelligence, image generation has taken center stage, allowing developers to create stunning visuals with minimal effort. The automioai/carlosescobar93 Cognitive Actions provide a powerful toolset for generating and refining images through an innovative inpainting process. By using these pre-built actions, developers can easily integrate advanced image manipulation capabilities into their applications, making creative projects more accessible and dynamic.

Prerequisites

Before diving into the integration of these Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic knowledge of making HTTP requests and handling JSON data.
  • Familiarity with Python (or another programming language) for implementing the API calls.

Authentication typically involves passing your API key in the headers of your requests, allowing secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Inpainted Images

The Generate Inpainted Images action empowers users to create and refine images by selectively masking and modifying them based on textual prompts. This action supports various customization options like scheduler algorithms and refinement styles, enhancing both image quality and creative control.

Input

The input schema for this action consists of several properties that guide the image generation process:

  • mask (string, URI): An input mask's URI used in inpaint mode. Black areas will be preserved, while white areas will be inpainted.
  • seed (integer, optional): Random seed for result variability. Leave blank to use a randomized seed.
  • image (string, URI): URI to the input image for img2img or inpaint mode.
  • width (integer, default 1024): The output image's width in pixels.
  • height (integer, default 1024): The output image's height in pixels.
  • prompt (string, default "An astronaut riding a rainbow unicorn"): A textual description guiding the image generation.
  • loraScale (number, default 0.6): Additive scale for the LoRA model, ranging from 0 to 1.
  • customWeights (string, optional): Specify custom LoRA weights to use.
  • guidanceScale (number, default 7.5): Guidance scale for classifier-free guidance. Range: 1 to 50.
  • applyWatermark (boolean, default true): Determines if a watermark is applied to the generated image.
  • negativePrompt (string, optional): Input prompt specifying undesirable elements in the generated image.
  • promptStrength (number, default 0.8): Strength of the input prompt effect. A value of 1 results in complete alteration of the original image.
  • schedulingType (string, default "K_EULER"): Define the sampling strategy for image generation.
  • numberOfOutputs (integer, default 1): Specifies the number of images to generate. Range: 1 to 4.
  • refinementSteps (integer, optional): The refinement step count when using base_image_refiner.
  • refinementStyle (string, default "no_refiner"): Select the style of refinement to apply.
  • highNoiseFraction (number, default 0.8): Fraction of noise applied when using the expert_ensemble_refiner.
  • disableSafetyChecker (boolean, default false): Option to disable the safety checker for generated images.
  • numberOfInferenceSteps (integer, default 50): The total number of denoising steps in image generation.

Example Input:

{
  "width": 768,
  "height": 768,
  "prompt": "a photo of TOK, with weird white hair, piercings in the noise and blue eyes",
  "loraScale": 0.6,
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "underexposed, weird face, clothes",
  "promptStrength": 0.8,
  "schedulingType": "K_EULER_ANCESTRAL",
  "numberOfOutputs": 2,
  "refinementStyle": "no_refiner",
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 30
}

Output

The output typically includes an array of URIs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/c5e90422-144c-41aa-986e-873ab0d63495/4fed30e0-6cdb-4232-8dff-30df9a33d439.png",
  "https://assets.cognitiveactions.com/invocations/c5e90422-144c-41aa-986e-873ab0d63495/f6e76242-22b7-4733-85b9-3110de81e669.png"
]

Conceptual Usage Example (Python)

Here's how you might call the Generate Inpainted Images action using 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 = "fbf21c18-20e4-46ab-907d-a06ea142c0bd"  # Action ID for Generate Inpainted Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 768,
    "height": 768,
    "prompt": "a photo of TOK, with weird white hair, piercings in the noise and blue eyes",
    "loraScale": 0.6,
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "negativePrompt": "underexposed, weird face, clothes",
    "promptStrength": 0.8,
    "schedulingType": "K_EULER_ANCESTRAL",
    "numberOfOutputs": 2,
    "refinementStyle": "no_refiner",
    "highNoiseFraction": 0.8,
    "numberOfInferenceSteps": 30
}

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, the action ID is specified, and the input payload is structured according to the defined schema. The endpoint URL and request structure are illustrative and should be adjusted according to your actual implementation.

Conclusion

The automioai/carlosescobar93 Cognitive Actions provide an exciting opportunity for developers to integrate sophisticated image generation capabilities into their applications. With the ability to create inpainted images using customizable prompts and various refinement options, the potential use cases are vast and varied. Whether you're building creative applications, enhancing visual content, or exploring artistic expression, these actions can significantly streamline your workflow. Start experimenting today and unlock the full potential of AI-driven image generation!

← Back to All Articles