Generate Stunning Images from Text with Centerfold XI DMD2 Cognitive Actions

23 Apr 2025
Generate Stunning Images from Text with Centerfold XI DMD2 Cognitive Actions

In the ever-evolving field of artificial intelligence, the ability to generate realistic images from textual descriptions is a groundbreaking innovation. The Centerfold XI DMD2 by TiwazM provides developers with pre-built Cognitive Actions that simplify this complex process. These actions allow you to create stunning images based on your text prompts, with customizable parameters to fine-tune the image characteristics. This guide will walk you through the key features of the Generate Realistic Image from Text action and how to integrate it into your applications.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Basic understanding of how to work with JSON and API requests.
  • Familiarity with Python programming for the conceptual usage examples provided in this article.

To authenticate your requests, you will typically include your API key in the request headers.

Cognitive Actions Overview

Generate Realistic Image from Text

Description:
This action generates realistic images from text prompts using the centerfold-xi-dmd2 model. You can customize various characteristics of the images, such as width, height, and style.

Category: image-generation

Input

The input for this action follows the CompositeRequest schema, which includes:

  • seed (integer, optional): The seed for generation; set to -1 to use a random seed.
    Example: -1
  • model (string, required): Specifies the model to use for generation.
    Example: "centerfold-xi-dmd2"
  • steps (integer, optional): Number of steps used during generation, ranging from 1 to 100.
    Example: 12
  • width (integer, optional): Width of the generated image (1 to 4096 pixels).
    Example: 1024
  • height (integer, optional): Height of the generated image (1 to 4096 pixels).
    Example: 1024
  • prompt (string, required): Input prompt in Compel weighting syntax to guide image generation.
    Example: "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V"
  • scheduler (string, optional): Specifies the scheduling algorithm to use during generation.
    Example: "Euler a"
  • configScale (number, optional): CFG scale determines the strength of adherence to the prompt.
    Example: 1.2
  • clipLayerSkip (integer, optional): Number of CLIP layers to skip.
    Example: 1
  • imageBatchSize (integer, optional): Number of images to generate (1 to 4).
    Example: 1
  • negativeGenPrompt (string, optional): Specifies undesirable elements.
    Example: "nsfw, naked"
  • guidanceNoiseRescale (number, optional): Adjustment level for rescaling CFG noise.
    Example: 0.5
  • prependInitialPrompt (boolean, optional): Whether to prepend a predefined pre-prompt.
    Example: true
  • variationalAutoencoder (string, optional): The VAE to use for generation.
    Example: "default"
  • progressiveAttentionScale (number, optional): Enhances CFG results if set above 0.
    Example: 0

Example Input:

{
  "seed": -1,
  "model": "centerfold-xi-dmd2",
  "steps": 12,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "scheduler": "Euler a",
  "configScale": 1.2,
  "clipLayerSkip": 1,
  "imageBatchSize": 1,
  "negativeGenPrompt": "nsfw, naked",
  "guidanceNoiseRescale": 0.5,
  "prependInitialPrompt": true,
  "variationalAutoencoder": "default",
  "progressiveAttentionScale": 0
}

Output

The action typically returns a URL to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e0cd71e4-d787-40bd-a902-652385e15285/c5ab5ead-bb4c-4623-b642-8ccf779289a3.png"
]

Conceptual Usage Example (Python)

Here's how you might call the Generate Realistic Image from Text 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 = "55948474-b7d4-44bf-9736-6defd2055471" # Action ID for Generate Realistic Image from Text

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "model": "centerfold-xi-dmd2",
    "steps": 12,
    "width": 1024,
    "height": 1024,
    "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
    "scheduler": "Euler a",
    "configScale": 1.2,
    "clipLayerSkip": 1,
    "imageBatchSize": 1,
    "negativeGenPrompt": "nsfw, naked",
    "guidanceNoiseRescale": 0.5,
    "prependInitialPrompt": true,
    "variationalAutoencoder": "default",
    "progressiveAttentionScale": 0
}

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 payload is constructed based on the required input schema, and the request is sent to the hypothetical endpoint. The response is then printed out.

Conclusion

The Generate Realistic Image from Text action from the Centerfold XI DMD2 model offers a robust tool for developers looking to enhance their applications with AI-generated imagery. By utilizing the customizable parameters provided, you can create tailored images that meet your project needs. Consider exploring various prompts and adjustments to discover the full potential of this Cognitive Action. Happy coding!

← Back to All Articles