Unlocking Image Creation: Integrate MyRealPony V2 Cognitive Actions

22 Apr 2025
Unlocking Image Creation: Integrate MyRealPony V2 Cognitive Actions

Introduction

In the ever-evolving realm of artificial intelligence, image generation stands as a fascinating frontier. The MyRealPony V2 Cognitive Actions offer developers a powerful API that simplifies the process of creating high-resolution images based on detailed prompts. By utilizing these pre-built actions, you can enhance your applications with stunning visuals without needing extensive knowledge of image processing.

Prerequisites

Before you start integrating the MyRealPony V2 Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform. This key will be used to authenticate your requests.
  • A basic understanding of JSON and how to structure API requests.

Typically, authentication involves passing your API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Image with MyRealPony V2

The Generate Image with MyRealPony V2 action allows you to create high-resolution images guided by detailed prompts. This action supports various configurations for image refinement, upscaling, and detail enhancement.

Input

The input for this action is a JSON object that can include the following fields:

  • seed: (integer) The seed for generation; use -1 for a random seed.
  • model: (string) Model to use for generation. Default is "MyRealPony-v2".
  • steps: (integer) The number of steps for the generation process (1-100).
  • width: (integer) Width of the generated image in pixels (1-4096).
  • height: (integer) Height of the generated image in pixels (1-4096).
  • prompt: (string) The detailed prompt for image generation.
  • refiner: (boolean) Enable the image refiner.
  • upscale: (string) Scaling factor (Options: Original, x2, x4, x8).
  • scheduler: (string) Scheduling algorithm for generation.
  • clipLayerSkip: (integer) Number of CLIP layers to skip.
  • prependPrompt: (boolean) Whether to prepend a preprompt.
  • negativePrompt: (string) Attributes to exclude from the generated image.
  • autoDetailerFace: (boolean) Activate the ADetailer model for face details.
  • autoDetailerHand: (boolean) Activate the ADetailer model for hand details.
  • cfgAttentionScale: (number) CFG scale to dictate model prompt attention level.
  • pagAttentionScale: (number) PAG scale to improve results.
  • autoDetailerPerson: (boolean) Activate the ADetailer model for person details.
  • guidanceRescaleAmount: (number) Rescale CFG-generated noise.
  • variationalAutoencoder: (string) Selects the Variational Autoencoder (VAE) for decoding images.

Here’s an example of the input payload:

{
  "seed": -1,
  "model": "MyRealPony-v2",
  "steps": 40,
  "width": 1080,
  "height": 1080,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "upscale": "Original",
  "scheduler": "DPM++ 2M SDE Karras",
  "clipLayerSkip": 1,
  "prependPrompt": true,
  "negativePrompt": "nsfw, naked",
  "autoDetailerFace": true,
  "autoDetailerHand": false,
  "cfgAttentionScale": 3.5,
  "pagAttentionScale": 0,
  "autoDetailerPerson": false,
  "guidanceRescaleAmount": 1,
  "variationalAutoencoder": "NeptuniaXL-VAE-ContrastSaturation"
}

Output

Upon executing this action, you will receive a response containing the URL of the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/7324421a-802f-441d-a0c8-4caecb99fa60/eee8caff-71ad-4d5c-8df7-0ad65ed1c68d.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might call the Cognitive Actions endpoint to generate an image:

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 = "3be60d2f-737d-4327-a22b-89ad616ef232"  # Action ID for Generate Image with MyRealPony V2

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "model": "MyRealPony-v2",
    "steps": 40,
    "width": 1080,
    "height": 1080,
    "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
    "upscale": "Original",
    "scheduler": "DPM++ 2M SDE Karras",
    "clipLayerSkip": 1,
    "prependPrompt": True,
    "negativePrompt": "nsfw, naked",
    "autoDetailerFace": True,
    "autoDetailerHand": False,
    "cfgAttentionScale": 3.5,
    "pagAttentionScale": 0,
    "autoDetailerPerson": False,
    "guidanceRescaleAmount": 1,
    "variationalAutoencoder": "NeptuniaXL-VAE-ContrastSaturation"
}

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, you replace the YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload structure corresponds to the required input schema for the action, and this example showcases how to handle responses and potential errors gracefully.

Conclusion

The MyRealPony V2 Cognitive Actions provide a robust platform for generating high-quality images based on detailed descriptions. By leveraging this action, you can enrich your applications with unique visual content that captures users' imaginations. Explore the capabilities of these actions and consider how they can enhance your current projects or inspire new ideas!

← Back to All Articles