Create Stunning Dark Mood Images with the dmitru/sdxl-darky Cognitive Actions

22 Apr 2025
Create Stunning Dark Mood Images with the dmitru/sdxl-darky Cognitive Actions

In the world of digital art, creating unique images that resonate with specific styles can be a challenge. The dmitru/sdxl-darky Cognitive Actions offer a powerful solution by allowing developers to generate dark, moody styled images using a fine-tuned SDXL model. This API provides a range of customization options, enabling users to incorporate their creative vision into the generated images. In this blog post, we will explore the capabilities of this action, along with how to effectively integrate it into your applications.

Prerequisites

Before diving into the integration, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic familiarity with making HTTP requests in your preferred programming language.

To authenticate, you typically pass the API key in the request headers.

Cognitive Actions Overview

Generate Dark Moody Styled Images

The Generate Dark Moody Styled Images action allows you to create visually striking images in a dark, moody aesthetic. This action is ideal for developers looking to generate artwork for gaming, storytelling, or artistic projects with a unique visual flair.

Input

The input for this action is structured as follows:

{
  "width": 1024,
  "height": 1024,
  "prompt": "an abstract psychedelic collage of photos and sketches made in the style of TOK. An imagined magic animal with human face",
  "loraScale": 0.8,
  "refineStyle": "expert_ensemble_refiner",
  "addWatermark": true,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.94,
  "executionScheduler": "K_EULER",
  "inferenceStepCount": 50,
  "inputPromptStrength": 0.8,
  "negativeInputPrompt": "",
  "classifierGuidanceScale": 7.5
}

Here’s the breakdown of the required and optional fields:

  • width (integer): Width of the output image in pixels (default: 1024).
  • height (integer): Height of the output image in pixels (default: 1024).
  • prompt (string): Text prompt to guide image generation (default: "An astronaut riding a rainbow unicorn").
  • loraScale (number): Scaling factor for LoRA models (default: 0.6).
  • refineStyle (string): Style of refinement to apply (default: "no_refiner").
  • addWatermark (boolean): Apply a watermark to the generated image (default: true).
  • numberOfOutputs (integer): Number of images to generate (default: 1; max 4).
  • highNoiseFraction (number): Noise fraction for refinement (default: 0.8).
  • executionScheduler (string): Scheduling algorithm for execution (default: "K_EULER").
  • inferenceStepCount (integer): Number of denoising steps (default: 50).
  • inputPromptStrength (number): Strength of the input prompt (default: 0.8).
  • negativeInputPrompt (string): Constraints to avoid during generation.
  • classifierGuidanceScale (number): Scale factor for classifier-free guidance (default: 7.5).

Output

The action returns a URL to the generated image, for example:

[
  "https://assets.cognitiveactions.com/invocations/01a5b4ff-f51e-4559-8272-392ee232729f/9abb1657-93d0-4492-9147-b682625c8353.png"
]

This URL points to the image created based on the specified input parameters.

Conceptual Usage Example (Python)

Below is a conceptual example of how you might call this action using Python. This snippet demonstrates how to structure the input payload correctly:

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 = "b02c4d81-61c9-4fbd-91a9-36e0be22334d" # Action ID for Generate Dark Moody Styled Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "an abstract psychedelic collage of photos and sketches made in the style of TOK. An imagined magic animal with human face",
    "loraScale": 0.8,
    "refineStyle": "expert_ensemble_refiner",
    "addWatermark": true,
    "numberOfOutputs": 1,
    "highNoiseFraction": 0.94,
    "executionScheduler": "K_EULER",
    "inferenceStepCount": 50,
    "inputPromptStrength": 0.8,
    "negativeInputPrompt": "",
    "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 code, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is constructed using the previously defined input schema, while the output is expected to provide the image URL upon successful execution.

Conclusion

The dmitru/sdxl-darky Cognitive Actions provide an exciting opportunity for developers to create dark, moody styled images effortlessly. With a variety of customizable parameters, this action can fit a range of projects, from digital art to creative storytelling. Considering the growing demand for unique visual content, integrating these actions into your applications can significantly enhance user engagement and creativity. Explore the possibilities today and start generating stunning images!

← Back to All Articles