image-generation

Create Stunning Glass-Inspired Images with Cognitive Actions

26 Apr 2025
Create Stunning Glass-Inspired Images with Cognitive Actions

The "Sdxl Lcm Glass1" service offers developers a powerful way to generate stunning images inspired by the artistry of the Corning Museum of Glass. By leveraging advanced models like Stable Diffusion XL, LCM, and LoRa, this service simplifies the image creation process, enabling users to produce beautiful visuals with just a few inputs. Whether you're creating marketing materials, enhancing digital content, or exploring artistic projects, these Cognitive Actions provide a quick and efficient solution to meet your creative needs.

Imagine the possibilities: transforming simple prompts into breathtaking images, customizing dimensions, applying watermarks, and even controlling the level of detail in your creations. This service is ideal for artists, marketers, and developers who want to incorporate unique, glass-inspired visuals into their work. With the ability to generate multiple images at once and fine-tune various parameters, you'll have complete control over the creative process.

Prerequisites

To get started with the Sdxl Lcm Glass1 service, you'll need a Cognitive Actions API key and a basic understanding of making API calls. This will allow you to easily integrate the image generation capabilities into your projects.

Generate Glass-Inspired Image

The "Generate Glass-Inspired Image" action enables developers to create unique images that draw inspiration from the intricate designs found in glass art. This action addresses the need for high-quality, visually appealing content that can enhance various applications, from e-commerce to social media.

Input Requirements

To use this action, you will need to provide the following inputs:

  • Prompt: A descriptive text guiding the image generation process.
  • Image: A URI of the input image, used in img2img or inpainting modes.
  • Mask: A URI for an input mask for inpainting (optional).
  • Width and Height: Dimensions of the output image in pixels (default is 1024).
  • Seed: A random seed for image generation (optional).
  • Guidance Scale: Intensity of classifier-free guidance (default is 2).
  • Number of Outputs: Total images to generate (default is 1).
  • Number of Inference Steps: Specifies the number of denoising steps (default is 6).
  • Apply Watermark: Option to apply a watermark to the generated image (default is true).
  • Prompt Strength and Lora Scale: Controls the transformation strength and LoRA component scaling, respectively (defaults are 0.8 and 0.6).

Example Input

{
  "seed": 2,
  "image": "https://replicate.delivery/pbxt/JvnFqHX4Moir5tba0MokREnmS5VbeogGZBYOjDywHdzX0VuE/99012-nyan-cat-png-image-high-quality.png",
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of <s0><s1> someone has made a lovely flower brooch on a white plate",
  "loraScale": 0.6,
  "scheduler": "LCM",
  "guidanceScale": 2,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.98,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 6
}

Expected Output

The action will produce an array of generated images based on the provided parameters. For instance:

[
  "https://assets.cognitiveactions.com/invocations/16388f67-862f-43ab-aa67-189cfa0498d4/d7d153f0-a56c-48bc-b18d-596e8730c9fd.png"
]

Use Cases for this Action

  • Artistic Projects: Artists can use this action to generate unique visuals that reflect their creative vision, perfect for exhibitions or portfolios.
  • Marketing Materials: Marketers can create eye-catching images for promotional materials, social media posts, or online advertisements, helping to attract and engage customers.
  • Content Creation: Bloggers and content creators can enhance their articles or videos with stunning visuals that complement their narratives, making their content more appealing.

```python
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "51e940e8-79b9-427f-809e-3938057f48ee" # Action ID for: Generate Glass-Inspired Image

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "seed": 2,
  "image": "https://replicate.delivery/pbxt/JvnFqHX4Moir5tba0MokREnmS5VbeogGZBYOjDywHdzX0VuE/99012-nyan-cat-png-image-high-quality.png",
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of <s0><s1> someone has made a lovely flower brooch on a white plate",
  "loraScale": 0.6,
  "scheduler": "LCM",
  "guidanceScale": 2,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.98,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 6
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")



## Conclusion

The Sdxl Lcm Glass1 service provides an innovative way to create captivating glass-inspired images, streamlining the process for developers and creatives alike. By harnessing the power of advanced image generation models, users can produce high-quality visuals tailored to their specific needs. Whether you're looking to enhance your marketing efforts, create stunning artwork, or simply explore the realm of digital creativity, this service opens up a world of possibilities. 

To get started, obtain your API key and experiment with the various parameters to see how you can elevate your projects with beautiful, unique images.
← Back to All Articles