Create Stunning Images with Wavyfusion Cognitive Actions

23 Apr 2025
Create Stunning Images with Wavyfusion Cognitive Actions

In the world of AI and machine learning, generating images from textual descriptions has gained remarkable traction. The Wavyfusion Cognitive Actions provide developers with the ability to create diverse and stylistically varied images using a sophisticated dreambooth model. By leveraging pre-built actions, developers can integrate complex image generation functionality into their applications without needing extensive expertise in AI. This guide will walk you through the capabilities of the Wavyfusion Cognitive Actions, specifically focusing on the Generate Wavyfusion Image action.

Prerequisites

Before you dive into using the Wavyfusion Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of JSON structures and HTTP requests.

Authentication typically involves passing your API key in the headers of your requests, allowing you to securely access the image generation capabilities.

Cognitive Actions Overview

Generate Wavyfusion Image

The Generate Wavyfusion Image action allows you to create images based on textual prompts, drawing from a diverse dataset that includes everything from photographs to paintings.

Input

The input for this action requires a JSON object that includes several properties, some of which are optional. Below is the schema and an example input:

{
  "width": 512,
  "height": 512,
  "prompt": "batman wa-vy style",
  "scheduler": "DPMSolverMultistep",
  "guidanceScale": 7.5,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}
  • seed (optional): Random seed value for image generation. Leave blank to allow randomization.
  • width (required): Width of the output image in pixels. Options include 128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, and 1024 (default is 512).
  • height (required): Height of the output image in pixels. Same options as width (default is 512).
  • prompt (required): Input textual prompt that guides the image generation process.
  • scheduler (optional): Select a scheduler for the image generation. Options include DDIM, K_EULER, and DPMSolverMultistep (default is K_EULER).
  • guidanceScale (optional): Scale for classifier-free guidance (default is 7.5, range 1 to 20).
  • negativePrompt (optional): Specify features to avoid in the output image.
  • promptStrength (optional): Influence of the prompt when using an initial image (default is 0.8).
  • numberOfOutputs (optional): Number of images to generate (range 1 to 4, default is 1).
  • numberOfInferenceSteps (optional): Number of denoising steps (default is 50, range 1 to 500).

Output

Upon successful execution, the action typically returns a JSON array containing URLs of the generated images. An example output could look like this:

[
  "https://assets.cognitiveactions.com/invocations/a35ad974-e3a4-44c6-ae00-20e31b0bb18d/10840d2f-7ad0-4c25-955c-ae2c319de8e8.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet demonstrating how to call the Generate Wavyfusion Image action using a hypothetical Cognitive Actions execution 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 = "88f8f420-4583-43df-9b67-308207949ed5" # Action ID for Generate Wavyfusion Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 512,
    "height": 512,
    "prompt": "batman wa-vy style",
    "scheduler": "DPMSolverMultistep",
    "guidanceScale": 7.5,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "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 snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The input payload is structured to match the required fields for the Generate Wavyfusion Image action.
  • The endpoint URL and request structure provided are illustrative.

Conclusion

The Wavyfusion Cognitive Actions, especially the Generate Wavyfusion Image action, empower developers to easily create visually compelling images from textual descriptions. By utilizing these pre-built actions, you can enhance your applications with advanced image generation capabilities while saving time and resources. Explore the various parameters to customize your image outputs and consider how you can apply this functionality in your projects!

← Back to All Articles