Elevate Your Image Processing with the gelsongraph/gelson21 Cognitive Actions

23 Apr 2025
Elevate Your Image Processing with the gelsongraph/gelson21 Cognitive Actions

In the realm of digital creativity, the ability to manipulate and generate images is paramount. The gelsongraph/gelson21 API offers a powerful set of Cognitive Actions designed for image processing, allowing developers to generate high-quality inpainted images through specified prompts and parameters. Whether you want to enhance existing images or create entirely new ones, these pre-built actions simplify the integration process into your applications.

Prerequisites

To utilize the Cognitive Actions provided by the gelsongraph/gelson21 API, you'll need a few essentials:

  • API Key: You'll require an API key to authenticate your requests. This key should be passed in the headers of your API calls.
  • Basic Understanding of JSON: Since the API utilizes JSON for input and output payloads, familiarity with this format is important.

Cognitive Actions Overview

Generate Inpainted Image

The Generate Inpainted Image action is designed to create high-quality inpainted images using specified prompts and parameters. This action can accept optional mask and image inputs, allowing for enhanced image-to-image transformations and control over output characteristics such as width, height, and format.

Input

The input schema for this action includes the following fields:

  • prompt (required): A text prompt guiding the image generation (e.g., a description of the desired image).
  • image (optional): A URI for an input image to be transformed.
  • mask (optional): A URI for an image mask for inpainting mode.
  • width (optional): Specifies the generated image's width (when aspect ratio is custom).
  • height (optional): Specifies the generated image's height (when aspect ratio is custom).
  • aspectRatio (optional): Defines the aspect ratio for the generated image; defaults to "1:1".
  • numOutputs (optional): Number of images to generate (1 to 4).
  • outputFormat (optional): The format of the output image (e.g., "webp", "jpg", "png").
  • guidanceScale (optional): Controls the guidance scale for the diffusion process.
  • outputQuality (optional): Specifies the quality of the output images (0 to 100).

Example Input:

{
  "image": "https://replicate.delivery/pbxt/LkyFAsewNh0ZmlukzPd9AdW6F4NxgmGXXwBGWSKrgwaA6247/img.webp",
  "prompt": "Photograph of gelson21 submerged in water, seemingly floating or swimming underwater. He is wearing a black tank top and tight black pants. The background appears to be a dark aquatic environment. In the background there is a laboratory glassware as if it were all a futuristic experiment. Blue lights and lasers. The style of the image is artistic, with a calm and mysterious atmosphere, possibly depicting a dreamlike or conceptual scene.",
  "loraScale": 1,
  "numOutputs": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 1,
  "numInferenceSteps": 28
}

Output

The output of this action typically returns an array of URIs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/3ceab757-570c-486a-9a8e-0b1da3005cb3/bb149d0e-7713-4160-930f-ccd87ac7d62b.webp"
]

Conceptual Usage Example (Python)

Here's how you could conceptually call the Generate Inpainted Image 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 = "2f427b04-dcb6-4d2e-9c38-1fd4873f6219" # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/LkyFAsewNh0ZmlukzPd9AdW6F4NxgmGXXwBGWSKrgwaA6247/img.webp",
    "prompt": "Photograph of gelson21 submerged in water, seemingly floating or swimming underwater. He is wearing a black tank top and tight black pants.",
    "loraScale": 1,
    "numOutputs": 1,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 1,
    "numInferenceSteps": 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, ensure you replace the API key and endpoint accordingly. The payload variable is structured based on the required inputs for the action.

Conclusion

The gelsongraph/gelson21 Cognitive Actions provide a robust framework for developers looking to incorporate advanced image processing capabilities into their applications. With the ability to generate high-quality inpainted images based on dynamic input parameters, you can easily create stunning visuals tailored to your needs. Explore these actions further to unlock their full potential in your projects!

← Back to All Articles