Create Stunning Shroomie Images with sakemin/shroomie-diffusion Cognitive Actions

23 Apr 2025
Create Stunning Shroomie Images with sakemin/shroomie-diffusion Cognitive Actions

In the world of image generation, the sakemin/shroomie-diffusion API offers a powerful toolset for developers looking to create unique and whimsical images of Shroomie the dog. With its fine-tuned SDXL model, this API allows users to utilize text prompts and various customization options to generate images that are as creative as they are captivating. By leveraging pre-built Cognitive Actions, developers can easily integrate advanced image generation capabilities into their applications.

Prerequisites

To get started with the sakemin/shroomie-diffusion Cognitive Actions, you'll need an API key that grants access to the service. Typically, this key is passed in the headers of your requests to authenticate your application. Make sure to obtain your key from the Cognitive Actions platform and keep it secure.

Cognitive Actions Overview

Generate Shroomie Images

The Generate Shroomie Images action is designed to create images of Shroomie the dog based on user-defined text prompts. It provides a wide range of customization options, including image dimensions, styles, and the ability to apply various refinements.

Input Schema:

The input schema for this action consists of several fields, both required and optional. Here's a breakdown:

  • prompt (string): The text prompt from which the output image is generated (e.g., "SHRMI dog swimming in outer space").
  • width (integer): Width of the output image in pixels (default: 1024).
  • height (integer): Height of the output image in pixels (default: 1024).
  • refineStyle (string): Selects the refinement style during generation (default: "no_refiner").
  • applyWatermark (boolean): Indicates whether to apply a watermark (default: true).
  • numberOfOutputs (integer): Specifies how many images to generate (default: 1, max: 4).
  • schedulingMethod (string): The scheduling method for denoising steps (default: "K_EULER").
  • highNoiseFraction (number): Specifies the fraction of noise to use (default: 0.8).
  • loraAdditiveScale (number): Scale factor for LoRA weights (default: 0.6).
  • inferenceStepCount (integer): The number of denoising steps (default: 50).
  • inputPromptStrength (number): Defines the strength of the input prompt in img2img/inpaint mode (default: 0.8).
  • negativeInputPrompt (string): Used to reduce certain features in the output image.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "SHRMI dog swimming in outer space",
  "refineStyle": "no_refiner",
  "applyWatermark": true,
  "numberOfOutputs": 1,
  "schedulingMethod": "K_EULER",
  "highNoiseFraction": 0.8,
  "loraAdditiveScale": 0.75,
  "inferenceStepCount": 50,
  "inputPromptStrength": 0.8,
  "negativeInputPrompt": "dog harness",
  "classifierGuidanceScale": 7.5
}

Output:

The action typically returns a URL pointing to the generated image. Here’s an example output:

[
  "https://assets.cognitiveactions.com/invocations/18226ce0-33ef-49a7-b718-0f43d95d4a40/d06b15b6-5a1e-4620-9372-fd5c6291dcbc.png"
]

Conceptual Usage Example (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 = "69b9a6d7-e41e-4044-8e11-d49838a8a3be" # Action ID for Generate Shroomie Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "SHRMI dog swimming in outer space",
    "refineStyle": "no_refiner",
    "applyWatermark": True,
    "numberOfOutputs": 1,
    "schedulingMethod": "K_EULER",
    "highNoiseFraction": 0.8,
    "loraAdditiveScale": 0.75,
    "inferenceStepCount": 50,
    "inputPromptStrength": 0.8,
    "negativeInputPrompt": "dog harness",
    "classifierGuidanceScale": 7.5
}

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 Python code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id is set to the ID for the Generate Shroomie Images action. The input payload is structured according to the action's requirements, and the response is printed out once the action is executed.

Conclusion

The sakemin/shroomie-diffusion Cognitive Actions provide a unique opportunity for developers to create stunning images of Shroomie the dog with ease. With various customization options, you can tailor the image generation process to fit your application’s needs. Whether you are looking to generate whimsical pet images or explore creative visual concepts, integrating these Cognitive Actions can elevate your project to new heights. Start experimenting today and unleash your creativity!

← Back to All Articles