Create Stunning Star Trek TNG Interiors with Cognitive Actions

23 Apr 2025
Create Stunning Star Trek TNG Interiors with Cognitive Actions

The fofr/sdxl-tng-interior Cognitive Actions provide developers with the ability to generate high-quality images of Star Trek Next Generation interiors using a fine-tuned SDXL model. These pre-built actions simplify the image generation process, allowing for inpainting, img2img transformations, and detailed customization of output characteristics. By leveraging these capabilities, developers can create visually stunning content that enhances user engagement in their applications.

Prerequisites

To get started with the Cognitive Actions for generating Star Trek TNG interiors, you'll need an API key for the Cognitive Actions platform. Generally, authentication can be achieved by passing this API key in the request headers. Ensure your development environment is set up to make HTTP requests.

Cognitive Actions Overview

Generate Star Trek TNG Interior Image

This action is designed to create high-quality images of Star Trek Next Generation interiors. Developers can customize various aspects of the image, such as size, prompt influence, and refinement strategies.

Input

The input schema for this action contains several properties, allowing for detailed customization:

  • mask (optional): URI of the input mask for inpaint mode.
  • seed (optional): Specifies the random seed for generating the image.
  • image (optional): URI of the input image for img2img or inpaint mode.
  • width (default: 1024): Specifies the width of the output image.
  • height (default: 1024): Specifies the height of the output image.
  • prompt (default: "An astronaut riding a rainbow unicorn"): Input prompt text to guide image generation.
  • loraScale (default: 0.6): LoRA scale factor for the pretrained model's weights.
  • refineMode (default: "no_refiner"): Refinement strategy for the generated image.
  • guidanceScale (default: 7.5): Scale factor for classifier-free guidance.
  • schedulerType (default: "K_EULER"): Algorithm used for image generation.
  • applyWatermark (default: true): Determines if a watermark is applied to the image.
  • negativePrompt (optional): Describes undesirable attributes for the image generation.
  • promptStrength (default: 0.8): Influences the img2img or inpaint result.
  • numberOfOutputs (default: 1): Specifies the number of images to generate.
  • refinementSteps (optional): Number of steps used to refine the image.
  • highNoiseFraction (optional): Specifies the fraction of noise added during refinement.
  • numberOfInferenceSteps (default: 50): Number of denoising steps used during image generation.

Example Input:

{
  "width": 1152,
  "height": 768,
  "prompt": "A photo in the style of TOK, interior, house - sustainable, minimalist, organic, light-filled, dynamic, efficient, autonomous, connected, harmonious, innovative, detailed, 8k, high resolution, sharp focus",
  "loraScale": 0.85,
  "refineMode": "expert_ensemble_refiner",
  "guidanceScale": 7.5,
  "schedulerType": "K_EULER",
  "applyWatermark": false,
  "negativePrompt": "low resolution, blurred, soft, jpeg artefacts, broken, distorted, ugly, disfigured",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.95,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns a URL pointing to the generated image. The output will be a link to a high-resolution image that reflects the prompt and customization parameters provided.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/4233610a-0dc4-47eb-9595-e707c4584d57/b847c6f8-5e71-4f36-a3ed-7b991b506842.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet that demonstrates how to call the Cognitive Actions execution endpoint to generate a Star Trek TNG interior image:

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 = "2fe249f2-13c8-40f9-835b-151befeb24f7"  # Action ID for Generate Star Trek TNG Interior Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1152,
    "height": 768,
    "prompt": "A photo in the style of TOK, interior, house - sustainable, minimalist, organic, light-filled, dynamic, efficient, autonomous, connected, harmonious, innovative, detailed, 8k, high resolution, sharp focus",
    "loraScale": 0.85,
    "refineMode": "expert_ensemble_refiner",
    "guidanceScale": 7.5,
    "schedulerType": "K_EULER",
    "applyWatermark": False,
    "negativePrompt": "low resolution, blurred, soft, jpeg artefacts, broken, distorted, ugly, disfigured",
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "highNoiseFraction": 0.95,
    "numberOfInferenceSteps": 50
}

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, make sure to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is structured according to the example input schema shown earlier, ensuring all necessary parameters are included.

Conclusion

The Cognitive Actions for generating Star Trek TNG interiors offer developers a powerful tool to create engaging and visually appealing content. By utilizing these actions, you can automate the image generation process, customize outputs, and enhance the overall user experience in your applications. Explore further use cases, experiment with different prompts, and integrate these actions into your projects to unlock the full potential of your creative ideas!

← Back to All Articles