Create Stunning Visuals with Majesty Diffusion Cognitive Actions

23 Apr 2025
Create Stunning Visuals with Majesty Diffusion Cognitive Actions

In the realm of image generation, the Majesty Diffusion API offers an exciting opportunity for developers to create visually captivating artwork from textual descriptions. By harnessing the power of CLIP-guided latent diffusion models, this API enables the generation of images that embody a unique 'royal' aesthetic, giving your applications a creative edge. With various configurations available, you can tailor the output to suit specific artistic needs, making it easier to integrate into any project.

Prerequisites

To utilize the Majesty Diffusion Cognitive Actions, you will need:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of how to make HTTP requests and handle JSON data.

Authentication typically involves passing your API key in the request headers. Ensure you have your key ready as you start integrating these actions into your applications.

Cognitive Actions Overview

Generate Images with Majesty Diffusion

This action allows you to generate images from text using the Majesty Diffusion model. It provides a range of configurations that include model selection, output size, and aesthetic preferences, enabling you to craft images that match your vision.

Input

The input for this action is structured as follows:

  • model (optional): Specifies the latent diffusion model to use. Options include "original", "finetuned", "ongo", and "erlich". Default is "finetuned".
  • width (optional): The width of the output image (options: 384, 512, 640, 768, 896, 1024). Default is 512.
  • height (optional): The height of the output image (options: 384, 512, 640, 768, 896, 1024). Default is 512.
  • initialMask (optional): URI of a mask image for inpainting.
  • initialImage (optional): URI of an initial image to use instead of noise.
  • initialTimestep (optional): Specifies the starting timestep for the diffusion process. Default is 0.9.
  • outputIntervals (optional): Interval of steps between each output (options: 0, 5, 10, 20). Default is 10.
  • clipInfluenceScale (optional): Defines the influence of CLIP prompts on the resulting image. Default is 9500.
  • clipGuidancePrompts (required): Text prompts for CLIP guidance, one prompt per line. Default is "The portrait of a Majestic Princess, trending on artstation".
  • latentGuidancePrompt (required): Single prompt for latent diffusion guidance. Default is "The portrait of a Majestic Princess, trending on artstation".
  • latentInfluenceScale (optional): Adjusts the impact of the latent prompt. Default is 13.5.
  • latentNegativePrompt (optional): Text prompts for features to avoid during diffusion.
  • advancedCustomSettings (optional): Configuration content for custom settings.
  • initialImageBrightness (optional): Adjusts the brightness of the initial image. Default is 0.
  • aestheticInfluenceScale (optional): Adjusts the aesthetic influence during image generation. Default is 400.
  • initialImageInfluenceScale (optional): Controls the influence of the initial image on the final output. Default is 1000.
Example Input
{
  "width": 640,
  "height": 768,
  "clipInfluenceScale": 16000,
  "clipGuidancePrompts": "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
  "latentGuidancePrompt": "vaporwave princess",
  "latentInfluenceScale": 12,
  "aestheticInfluenceScale": 400
}

Output

The output of this action typically consists of an array of URLs pointing to the generated images. Here’s an example of the output you might receive:

[
  "https://assets.cognitiveactions.com/invocations/63a0a1fc-300c-4a52-b34f-5dde6700b2ea/4dae2658-94fb-4992-8802-6aa53b9d92ab.png",
  "https://assets.cognitiveactions.com/invocations/63a0a1fc-300c-4a52-b34f-5dde6700b2ea/b6f9a328-78b7-4094-b537-2c49496a468a.png",
  ...
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might call the Majesty Diffusion action 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 = "eebfd093-1dd7-44b3-b4a6-77f145e50af3"  # Action ID for Generate Images with Majesty Diffusion

# Construct the input payload based on the action's requirements
payload = {
    "width": 640,
    "height": 768,
    "clipInfluenceScale": 16000,
    "clipGuidancePrompts": "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
    "latentGuidancePrompt": "vaporwave princess",
    "latentInfluenceScale": 12,
    "aestheticInfluenceScale": 400
}

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 the placeholder with your actual API key and the action ID. The input JSON payload is structured according to the requirements of the action, and the output will provide you with generated image URLs.

Conclusion

The Majesty Diffusion Cognitive Actions offer a powerful and flexible way to generate stunning visuals from textual descriptions. By leveraging the capabilities of this API, developers can create unique artwork tailored to their applications. Whether you're designing an art project, enhancing a game, or building a creative tool, integrating these actions can significantly enhance your application's visual appeal. Start experimenting with the Majesty Diffusion today and unlock your creative potential!

← Back to All Articles