Generate Stunning Victorian Era Images with the SDXL Actions

21 Apr 2025
Generate Stunning Victorian Era Images with the SDXL Actions

In the realm of image generation, the ability to create visually stunning and contextually rich images is a game-changer for developers. The davidbarker/sdxl-victorian-britain specification empowers you to generate Victorian-era images using cutting-edge technology. Through its sophisticated Cognitive Actions, developers can easily create and customize images that evoke the unique aesthetics of Victorian Britain, making it a perfect tool for applications in storytelling, education, and creative arts.

Prerequisites

Before diving into the Cognitive Actions, you will need to ensure you have access to the Cognitive Actions platform, including obtaining an API key for authentication. Generally, this involves passing your API key in the request headers. Here’s a conceptual overview:

  • API Key: Required for authentication; usually passed as a Bearer token in the headers of your requests.

Cognitive Actions Overview

Generate Victorian Era Image

Description: This action creates images in the style of photographs from Victorian-era Britain using the SDXL model. It allows for extensive customization through prompts, image refinement, and various parameters for image processing.

Category: image-generation

Input

The input schema for this action is quite detailed, allowing for a range of customizations:

  • mask (string, optional): Input mask for inpaint mode (URI).
  • seed (integer, optional): Random seed for generating variations.
  • image (string, optional): URI of the input image for img2img or inpaint mode.
  • width (integer, default: 1024): Width of the output image in pixels.
  • height (integer, default: 1024): Height of the output image in pixels.
  • prompt (string, required): Textual description for the desired output image.
  • refineStyle (string, default: "no_refiner"): Refinement style to apply.
  • scheduleType (string, default: "K_EULER"): Scheduler type to use during generation.
  • refinementSteps (integer, optional): Number of refinement steps.
  • outputImageCount (integer, default: 1): Number of output images to generate (1-4).
  • highNoiseFraction (number, default: 0.8): Noise fraction for the expert ensemble refiner.
  • loraAdditiveScale (number, default: 0.6): Scale of additive effect when using LoRA.
  • inferenceStepCount (integer, default: 50): Total number of denoising inference steps.
  • inputPromptStrength (number, default: 0.8): Strength of the input prompt.
  • negativeInputPrompt (string, optional): Elements to exclude from the image.
  • watermarkApplication (boolean, default: true): Indicates whether to apply a watermark.
  • classifierGuidanceScale (number, default: 7.5): Level of classifier-free guidance.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "Victorian-era photograph in the style of TOK, a man taking a selfie with a modern (((iPhone))), close-up",
  "refineStyle": "no_refiner",
  "scheduleType": "K_EULER",
  "outputImageCount": 1,
  "highNoiseFraction": 0.8,
  "loraAdditiveScale": 0.6,
  "inferenceStepCount": 50,
  "inputPromptStrength": 0.8,
  "negativeInputPrompt": "deformed, text, watermark, logo, banner, extra digits, deformed fingers, deformed hands, cropped, signature, username, error, sketch, duplicate, ugly, geometry, mutation, disgusting",
  "watermarkApplication": true,
  "classifierGuidanceScale": 7.5
}

Output

The output is a URI pointing to the generated image. Here’s an example of what the response might look like:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e638e6ea-6368-4de6-9800-f1eaff8b5940/8eae3f83-21b7-48c0-88ad-1b0d994f2a02.png"
]

Conceptual Usage Example (Python)

Here’s how you might call this action through a hypothetical Cognitive Actions endpoint:

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 = "65bd9fe5-6a91-4166-b7ac-d73fd2da30f4" # Action ID for Generate Victorian Era Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "Victorian-era photograph in the style of TOK, a man taking a selfie with a modern (((iPhone))), close-up",
    "refineStyle": "no_refiner",
    "scheduleType": "K_EULER",
    "outputImageCount": 1,
    "highNoiseFraction": 0.8,
    "loraAdditiveScale": 0.6,
    "inferenceStepCount": 50,
    "inputPromptStrength": 0.8,
    "negativeInputPrompt": "deformed, text, watermark, logo, banner, extra digits, deformed fingers, deformed hands, cropped, signature, username, error, sketch, duplicate, ugly, geometry, mutation, disgusting",
    "watermarkApplication": true,
    "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}
    )
    response.raise_for_status() 

    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, you can see how to structure the input payload according to the action's requirements. The action ID and the input payload are crucial for successfully executing the request.

Conclusion

The davidbarker/sdxl-victorian-britain Cognitive Actions provide a powerful toolkit for developers looking to create captivating Victorian-era images. By utilizing the detailed customization options available, you can fine-tune your outputs to meet specific artistic or thematic needs. Consider exploring various prompts and refinement styles to fully leverage the potential of this action in your projects. Happy coding!

← Back to All Articles