Create Stunning Images with the capim-labs/helbert_costa Cognitive Actions

25 Apr 2025
Create Stunning Images with the capim-labs/helbert_costa Cognitive Actions

In the world of image generation, the capim-labs/helbert_costa spec offers powerful Cognitive Actions designed for developers looking to create and manipulate images with precision. The key action in this spec, Generate Enhanced Image with Inpainting, allows for detailed image generation using a combination of input images and advanced inpainting techniques. This action provides flexibility in aspect ratios, guidance scales, and various models to enhance the results, making it an ideal choice for developers eager to integrate cutting-edge image processing into their applications.

Prerequisites

Before you start using the Cognitive Actions, ensure that you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic understanding of HTTP requests.
  • Ability to make HTTP requests in your preferred programming language.

For authentication, you will typically need to pass your API key in the headers of your requests.

Cognitive Actions Overview

Generate Enhanced Image with Inpainting

Description:
This action allows developers to generate detailed images by utilizing a combination of an input image and inpainting methods. With options for custom aspect ratios, model selection, and fine-tuning, you can create images that meet specific needs for both quality and speed.

Category: image-generation

Input

The input schema for this action is defined as follows:

  • prompt (required): The textual description guiding the image generation.
  • mask (optional): An image mask for inpainting mode.
  • seed (optional): A random seed for reproducible results.
  • image (optional): An input image for image-to-image transformation or inpainting.
  • model (optional): Choose between "dev" and "schnell" models, with "dev" optimized for quality and "schnell" for speed.
  • goFast (optional): A boolean to enable faster predictions.
  • width (optional): Specifies the width of the output image if using a custom aspect ratio.
  • height (optional): Specifies the height of the output image if using a custom aspect ratio.
  • numOutputs (optional): The number of images to generate.
  • aspectRatio (optional): Defines the aspect ratio of the generated image.
  • outputFormat (optional): The file format of the output images (webp, jpg, png).
  • guidanceScale (optional): Scale for the diffusion process.
  • outputQuality (optional): Quality setting for the output images.
  • promptStrength (optional): Strength of the prompt when using image-to-image generation.
  • numInferenceSteps (optional): Number of denoising steps for generating images.
  • additionalLoraScale (optional): Scale for any extra LoRA applied.
  • approximateMegapixels (optional): Estimated megapixels for the generated image.
  • safetyCheckerDisabled (optional): Enable or disable the safety checker for generated images.

Example Input:

{
  "model": "dev",
  "goFast": false,
  "prompt": "uma foto do Helbert na praia",
  "loraScale": 1,
  "numOutputs": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3,
  "outputQuality": 80,
  "promptStrength": 0.8,
  "numInferenceSteps": 28,
  "additionalLoraScale": 1,
  "approximateMegapixels": "1"
}

Output

The output of this action typically returns a URL to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/b839dd89-45ad-483b-b017-9d93e7ce9033/17c04fb8-cf43-4e34-bf34-146b497c35f9.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet demonstrating how to call this action:

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 = "05a74d8d-4ebb-4748-b5cf-282a302d4114"  # Action ID for Generate Enhanced Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "uma foto do Helbert na praia",
    "loraScale": 1,
    "numOutputs": 1,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3,
    "outputQuality": 80,
    "promptStrength": 0.8,
    "numInferenceSteps": 28,
    "additionalLoraScale": 1,
    "approximateMegapixels": "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, replace the placeholder API key and endpoint URL with your actual credentials. The payload variable is structured according to the input schema, and the request is sent to the hypothetical Cognitive Actions execution endpoint. The response contains the generated image's URL.

Conclusion

The capim-labs/helbert_costa Cognitive Actions provide robust tools for developers aiming to enhance their applications with advanced image generation capabilities. By leveraging actions like Generate Enhanced Image with Inpainting, you can create stunning visuals tailored to your requirements. Consider exploring various configurations of the input parameters to find the best results for your projects. Happy coding!

← Back to All Articles