Generate Stunning Images with the witzelfitz/gardenflux Cognitive Actions

23 Apr 2025
Generate Stunning Images with the witzelfitz/gardenflux Cognitive Actions

In the world of AI-driven creativity, the witzelfitz/gardenflux API offers powerful Cognitive Actions tailored for image generation, specifically through inpainting and image-to-image techniques. These pre-built actions allow developers to efficiently create stunning visuals with customizable parameters, enhancing their applications with advanced image capabilities. In this post, we will explore the primary action available in this spec and guide you on how to integrate it into your projects.

Prerequisites

Before getting started with the witzelfitz/gardenflux Cognitive Actions, you will need:

  • An API key to access the Cognitive Actions platform.
  • Basic understanding of JSON and RESTful API calls.

Authentication typically involves passing your API key in the request headers, allowing you to securely interact with the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting

Purpose:
This action allows you to generate images using advanced inpainting techniques. You can specify an image mask, input an existing image, or use various parameters to control the generation process, such as dimensions, quality, and model type.

Category: Image Generation

Input: The action requires a structured JSON input, primarily focusing on the prompt. Here’s a breakdown of the input schema:

  • prompt: (string, required) A detailed prompt that guides the image generation.
  • mask: (string, optional) A URI for the image mask used in inpainting mode.
  • image: (string, optional) A URI for the input image for inpainting.
  • width: (integer, optional) Width of the generated image (only for custom aspect ratio).
  • height: (integer, optional) Height of the generated image (only for custom aspect ratio).
  • goFast: (boolean, optional) Enables faster predictions using an optimized model.
  • aspectRatio: (string, optional) Specifies the aspect ratio of the output image.
  • imageFormat: (string, optional) Defines the format for saving the generated image (e.g., 'webp', 'jpg').
  • numOutputs: (integer, optional) Number of image variations to generate (default is 1).
  • guidanceScale: (number, optional) Controls the intensity of guidance during image generation.
  • outputQuality: (integer, optional) Sets the quality of the generated image.
  • (Additional parameters for fine control over image generation are also available.)

Example Input:

{
  "prompt": "swiss garden, vegetables, flowers, swimming pool",
  "loraScale": 1,
  "modelType": "schnell",
  "numOutputs": 1,
  "aspectRatio": "16:9",
  "imageFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 80,
  "extraLoraScale": 0.8,
  "numInferenceSteps": 4
}

Output: The action returns an array of generated image URLs based on the prompt and parameters provided.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/0e03060f-3c46-465d-945e-ca97a6bc3b8b/33e77253-242c-45c1-9e87-e8f8c7fe4a8c.webp"
]

Conceptual Usage Example (Python): Here’s how you might call the Generate Image with Inpainting 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 = "82636a61-64ac-43f6-a332-fa23e3e67700" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "swiss garden, vegetables, flowers, swimming pool",
    "loraScale": 1,
    "modelType": "schnell",
    "numOutputs": 1,
    "aspectRatio": "16:9",
    "imageFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 80,
    "extraLoraScale": 0.8,
    "numInferenceSteps": 4
}

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 snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The action_id is specified for the "Generate Image with Inpainting" action.
  • The payload is constructed based on the required inputs for the action.

Conclusion

The witzelfitz/gardenflux Cognitive Actions empower developers to leverage sophisticated image generation capabilities, streamlining the process of creating visually appealing content. By utilizing the Generate Image with Inpainting action, you can enhance your applications with custom-generated images tailored to your specifications.

Explore the potential of these Cognitive Actions and consider integrating them into your projects to unlock new creative possibilities!

← Back to All Articles