Create Stunning Image Variations with owengillett/winstondog Cognitive Actions

23 Apr 2025
Create Stunning Image Variations with owengillett/winstondog Cognitive Actions

In the world of digital creativity, the ability to generate unique images based on prompts can significantly enhance applications and user experiences. The owengillett/winstondog API provides a powerful Cognitive Action to create image variations from existing images using advanced techniques. This action, "Generate Image Variations," allows developers to harness the power of AI-driven image generation, offering customization options for dimensions, prompts, and more. By integrating this action, you can elevate your applications with dynamic and visually compelling content.

Prerequisites

Before you can start using the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which is essential for authentication.
  • Basic understanding of JSON and RESTful API concepts.

Typically, authentication works by passing your API key in the request headers, which allows you to access the functionalities securely.

Cognitive Actions Overview

Generate Image Variations

The Generate Image Variations action allows you to create variations from a specified image URI using img2img techniques. This action gives you control over various parameters such as prompt strength, number of outputs, and inference steps to refine your generated images.

Input

The input for this action is structured as follows:

{
  "seed": 10,
  "image": "https://example.com/image.png",
  "width": 512,
  "height": 512,
  "prompt": "a colonial era portrait of [winstondog], a dog sitting at a desk. Faces of America...",
  "scheduler": "DDIM",
  "guidanceScale": 8,
  "negativePrompt": "overexposed, low resolution...",
  "promptStrength": 1,
  "numberOfOutputs": 4,
  "disableSafetyCheck": false,
  "numberOfInferenceSteps": 100
}

Key Fields:

  • seed (integer): A seed for randomization. Leave blank to randomize.
  • image (string): URI of the starting image for generating variations.
  • width (integer): Width of the output image in pixels (default is 512).
  • height (integer): Height of the output image in pixels (default is 512).
  • prompt (string): Text prompt to influence image generation.
  • scheduler (string): The scheduler type to guide the image generation process (default is "DDIM").
  • guidanceScale (number): Scale for classifier-free guidance (default is 7.5).
  • negativePrompt (string): Specification of undesired elements to avoid in the output.
  • promptStrength (number): Strength of prompt influence when using an initial image (default is 0.8).
  • numberOfOutputs (integer): Specifies how many images to output (default is 1, max is 4).
  • numberOfInferenceSteps (integer): Total number of denoising steps (default is 50).

Output

Upon successful execution, the action returns an array of image URLs. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/.../image1.png",
  "https://assets.cognitiveactions.com/invocations/.../image2.png",
  "https://assets.cognitiveactions.com/invocations/.../image3.png",
  "https://assets.cognitiveactions.com/invocations/.../image4.png"
]

These URLs point to the generated image variations based on your input parameters.

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image Variations action using Python:

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 = "36b6cf51-489e-49b0-9302-e9e95a7ed8f9"  # Action ID for Generate Image Variations

# Construct the input payload based on the action's requirements
payload = {
    "seed": 10,
    "image": "https://example.com/image.png",
    "width": 512,
    "height": 512,
    "prompt": "a colonial era portrait of [winstondog], a dog sitting at a desk. Faces of America...",
    "scheduler": "DDIM",
    "guidanceScale": 8,
    "negativePrompt": "overexposed, low resolution...",
    "promptStrength": 1,
    "numberOfOutputs": 4,
    "numberOfInferenceSteps": 100
}

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, ensure you replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key and adjust the image URI as needed. The payload variable is structured according to the action's requirements.

Conclusion

The owengillett/winstondog Cognitive Action for generating image variations offers an exciting opportunity for developers to create dynamic visual content tailored to their applications' needs. With customizable options for prompts, dimensions, and outputs, you can harness this action to enhance user engagement and creativity in your projects. Consider exploring different prompts and configurations to see the diverse results you can achieve! Happy coding!

← Back to All Articles