Harness the Power of Image Generation with scornflake/sdxl-grasses Cognitive Actions

22 Apr 2025
Harness the Power of Image Generation with scornflake/sdxl-grasses Cognitive Actions

In the realm of creative design and digital art, the demand for stunning visuals is ever-increasing. The scornflake/sdxl-grasses API offers powerful Cognitive Actions that enable developers to create captivating images featuring New Zealand grasses and flaxes. By leveraging advanced image-to-image transformation techniques and inpainting modes, these actions provide a streamlined way to generate beautiful, custom visuals that can enhance various applications, from landscaping software to artistic projects.

Prerequisites

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

  • An API key for the Cognitive Actions platform, which you will use for authentication.
  • Basic knowledge of RESTful APIs and JSON for handling requests and responses.

Conceptually, you will pass your API key in the request headers to authenticate your requests.

Cognitive Actions Overview

Generate Image with NZ Grasses and Flaxes

This action allows you to create images that feature various New Zealand grasses and flaxes. By using image-to-image transformation or inpainting modes, you can customize the output with specific parameters like refinement style, scheduler algorithm, and more.

Category: image-generation

Input

The input for this action is structured as a JSON object that includes various customizable fields:

  • mask (string): URI for the input mask in inpaint mode. Black areas remain unchanged; white areas are subject to inpainting.
  • image (string): URI for the input image, used in img2img or inpaint mode.
  • width (integer): Specifies the width of the output image in pixels. Default is 1024.
  • height (integer): Specifies the height of the output image in pixels. Default is 1024.
  • prompt (string): Text prompt to guide image generation. Default is "An astronaut riding a rainbow unicorn".
  • refine (string): Selects the method for refining the image. Options: no_refiner, expert_ensemble_refiner, or base_image_refiner. Default is no_refiner.
  • scheduler (string): Specifies the scheduling algorithm to use. Default is K_EULER.
  • outputCount (integer): Number of images to generate (1 to 4). Default is 1.
  • guidanceScale (number): Scale for classifier-free guidance. Default is 7.5.
  • applyWatermark (boolean): Adds a watermark to the generated image. Default is true.
  • loraScaleValue (number): Specifies the additive scale for LoRA. Default is 0.6.
  • negativePrompt (string): Text prompt to be avoided in image generation. Default is an empty string.
  • promptIntensity (number): Defines the strength of the prompt. Default is 0.8.
  • highNoiseFraction (number): Specifies the amount of noise applied in some refining methods. Default is 0.8.
  • inferenceStepCount (integer): Number of denoising steps (1 to 500). Default is 50.

Example Input:

{
  "mask": "https://replicate.delivery/pbxt/LZdr8mcnk1c455HDSa6ni7bbiS93u0rCMp581p3HmYy6E6vZ/IMG_1002_front_only.png",
  "image": "https://replicate.delivery/pbxt/LZdr8pc7Ejkm2xDIlbfIrhmKXtohrZMUYf6N5CeSRcEU6Krd/IMG_1002.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "low-maintenance grasses and flaxes, on a bed of river stones.\n",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "outputCount": 1,
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "loraScaleValue": 0.6,
  "negativePrompt": "",
  "promptIntensity": 0.8,
  "highNoiseFraction": 0.8,
  "inferenceStepCount": 50
}

Output

This action returns a URL to the generated image based on the input parameters.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/49dcab26-07cb-492d-acb5-93ad7b1be874/2dbe4eb8-a85e-4df5-8946-2f4942aad666.png"
]

Conceptual Usage Example (Python)

Here’s how you might call this action using a hypothetical endpoint in 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 = "ac2459b8-adc8-473f-bf19-0751a0ff9c8e"  # Action ID for Generate Image with NZ Grasses and Flaxes

# Construct the input payload based on the action's requirements
payload = {
    "mask": "https://replicate.delivery/pbxt/LZdr8mcnk1c455HDSa6ni7bbiS93u0rCMp581p3HmYy6E6vZ/IMG_1002_front_only.png",
    "image": "https://replicate.delivery/pbxt/LZdr8pc7Ejkm2xDIlbfIrhmKXtohrZMUYf6N5CeSRcEU6Krd/IMG_1002.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "low-maintenance grasses and flaxes, on a bed of river stones.\n",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "outputCount": 1,
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "loraScaleValue": 0.6,
    "negativePrompt": "",
    "promptIntensity": 0.8,
    "highNoiseFraction": 0.8,
    "inferenceStepCount": 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}
    )
    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 the placeholders with your actual API key and endpoint. The payload variable is structured according to the action's requirements. This example illustrates how to send a request to generate an image using the specified parameters.

Conclusion

The scornflake/sdxl-grasses Cognitive Actions provide developers with powerful tools to generate stunning images of New Zealand grasses and flaxes. With customizable parameters, you can create unique visuals tailored to your needs. Now that you have a solid understanding of how to use these actions, consider exploring further applications in your projects, from enhancing digital art to creating realistic landscaping designs. Happy coding!

← Back to All Articles