image-generation

Create Stunning Visual Illusions with AI Image Generation

26 Apr 2025
Create Stunning Visual Illusions with AI Image Generation

In the world of digital art and design, the ability to create captivating visuals is paramount. The "Illusions" service provides developers with powerful Cognitive Actions that allow for the generation of high-quality visual illusions. By leveraging advanced image generation techniques, including image-to-image transformations, inpainting, and controlnet adjustments, this service simplifies the creative process and enhances productivity. Whether you're looking to create unique artwork, enhance existing images, or develop engaging visual content for applications, the Illusions service is designed to meet diverse creative needs.

Prerequisites

To get started with the Illusions service, you'll need a Cognitive Actions API key and a basic understanding of API call structures. This will enable you to seamlessly integrate the image generation capabilities into your projects.

Create Visual Illusions

Purpose

The "Create Visual Illusions" action is designed to generate stunning visual illusions using the Deliberate v2 model. This action allows developers to manipulate images creatively, making it possible to produce unique and eye-catching visuals that can captivate audiences.

Input Requirements

To utilize this action, you'll need to provide several inputs:

  • Seed: An integer that helps control the randomness of the output.
  • Image: An optional URI for an image to be processed (img2img).
  • Width and Height: Defines the dimensions of the output image.
  • Prompt: A text string that describes what the generated image should depict.
  • Mask Image: An optional URI for inpainting.
  • Control Image: An optional URI for additional guidance in the generation.
  • Exclude Prompt: A string to indicate what should not be included in the output.
  • Guidance Level: A number that sets the intensity of guidance during image generation.
  • Sizing Strategy: Determines how the output image is resized.
  • Number of Outputs: Specifies how many images to generate (1 to 4).
  • Prompt Intensity: Controls how much the prompt influences the final image.
  • Control Conditioning Start/End: Defines when controlnet conditioning begins and ends.
  • Control Conditioning Intensity: Sets the strength of controlnet conditioning.
  • Number of Inference Steps: Specifies how many diffusion steps to perform during generation.

Expected Output

The output will be a URI to the generated image, which will reflect the specifications provided in the input parameters.

Use Cases for this Specific Action

  • Digital Art Creation: Artists can use this action to generate unique pieces of artwork based on specific prompts or existing images.
  • Marketing and Advertising: Designers can create visually striking images for campaigns, ensuring they stand out in a crowded marketplace.
  • Game Development: Game developers can generate textures and visuals that enhance the gaming experience, making environments more immersive.
  • Social Media Content: Marketers and influencers can quickly create engaging visuals for social media platforms, boosting engagement and shares.
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 = "20bb67e7-c7f7-4ffc-9bbf-f423a951e8ae" # Action ID for: Create Visual Illusions

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "seed": -1,
  "image": "https://replicate.delivery/pbxt/JouANiZNiW2mwouIgIk1VySvjL9MBmaPD6Ib8HyfW81CJzRR/out-0-44.png",
  "width": 768,
  "height": 768,
  "prompt": "a painting of a 19th century town",
  "controlImage": "https://replicate.delivery/pbxt/JouAO2zaHgb66YVChJagSYz0LcGqv3QgG4BS71mioFbBHWTZ/spiral_black_transparent-2513050263.jpg",
  "excludePrompt": "ugly, disfigured, low quality, blurry, nsfw",
  "guidanceLevel": 7.5,
  "sizingStrategy": "width/height",
  "numberOfOutputs": 1,
  "promptIntensity": 0.75,
  "controlConditioningEnd": 1,
  "numberOfInferenceSteps": 40,
  "controlConditioningStart": 0,
  "controlConditioningIntensity": 0.75
}

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 Illusions service offers a robust set of tools for creating visually stunning images that can enhance various creative projects. By integrating the "Create Visual Illusions" action, developers can streamline their workflows and unlock new possibilities for artistic expression. Whether you're an artist, designer, or marketer, this service can help you generate captivating visuals that resonate with your audience. Explore the potential of AI-driven image generation and elevate your creative projects to new heights!

← Back to All Articles