Create Stunning Tileable Images with pwntus/material-diffusion-sdxl Cognitive Actions

25 Apr 2025
Create Stunning Tileable Images with pwntus/material-diffusion-sdxl Cognitive Actions

In the world of digital art and design, generating high-quality images that can be seamlessly tiled is a valuable skill. The pwntus/material-diffusion-sdxl API provides a powerful Cognitive Action that leverages the Stable Diffusion XL model to create stunning, tileable images. This action allows developers to customize various parameters such as image dimensions, guidance scale, and refinement styles, making it an excellent tool for artists and developers alike.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Basic understanding of JSON and HTTP requests.
  • Familiarity with Python (for the provided code examples).

Authentication generally involves passing your API key in the headers of your requests, allowing you to securely access the Cognitive Actions.

Cognitive Actions Overview

Generate Tileable Images with Stable Diffusion XL

Description: This action creates high-quality, tileable images using the Stable Diffusion XL model. Developers can customize image parameters to refine the output according to their needs.

Category: Image Generation

Input

The input schema for this action includes several customizable fields:

  • seed (integer): Specifies the random seed value. Leave blank for randomization.
  • prompt (string): The main input prompt that defines the desired thematic and stylistic elements.
    Example: "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k"
  • imageWidth (integer): Width of the output image (options: 128 to 1600). Example: 768
  • imageHeight (integer): Height of the output image (options: 128 to 1600). Example: 768
  • refineStyle (string): Selects the refinement style (options: no_refiner, expert_ensemble_refiner, base_image_refiner). Example: "expert_ensemble_refiner"
  • denoiseSteps (integer): Number of denoising steps (1 to 500). Example: 50
  • inversePrompt (string): A prompt to specify features to avoid.
  • noiseFraction (number): Fraction of noise to apply (0 to 1). Example: 0.8
  • scheduleMethod (string): Scheduler method for image generation (options: DDIM, DPMSolverMultistep, etc.). Example: "DDIM"
  • refinementSteps (integer): Number of refinement steps for base_image_refiner.
  • outputImageCount (integer): Number of images to generate (1 to 4). Example: 1
  • watermarkApplied (boolean): Applies a watermark for generated images. Example: true
  • guidanceIntensity (number): Scale for classifier-free guidance (1 to 50). Example: 7.5

Here's a practical example of the JSON payload needed to invoke the action:

{
  "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
  "imageWidth": 768,
  "imageHeight": 768,
  "refineStyle": "expert_ensemble_refiner",
  "denoiseSteps": 50,
  "noiseFraction": 0.8,
  "scheduleMethod": "DDIM",
  "outputImageCount": 1,
  "watermarkApplied": true,
  "guidanceIntensity": 7.5
}

Output

The action will typically return a URL to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/c5564ce5-53a4-49a0-a867-26af47da9340/882601bd-c96d-4254-a3b9-b7d1b5b278f9.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet demonstrating how you might call this Cognitive Action:

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 = "037b51fe-f26b-4018-bca0-ac38e9c7de50"  # Action ID for Generate Tileable Images with Stable Diffusion XL

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
    "imageWidth": 768,
    "imageHeight": 768,
    "refineStyle": "expert_ensemble_refiner",
    "denoiseSteps": 50,
    "noiseFraction": 0.8,
    "scheduleMethod": "DDIM",
    "outputImageCount": 1,
    "watermarkApplied": true,
    "guidanceIntensity": 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 code snippet, replace the API key and endpoint with your actual values. The payload variable contains the input required for generating tileable images, while headers include the necessary authentication.

Conclusion

The pwntus/material-diffusion-sdxl Cognitive Action for generating tileable images is a powerful tool for artists and developers looking to enhance their applications with high-quality imagery. By understanding the input parameters and utilizing the API effectively, you can create stunning visuals that meet your project's needs. Explore how you can integrate this action into your applications today!

← Back to All Articles