Enhance Your Applications with Image Generation Using maczzzzzzz/tang Actions

24 Apr 2025
Enhance Your Applications with Image Generation Using maczzzzzzz/tang Actions

In the ever-evolving landscape of digital content creation, the ability to generate unique images programmatically can significantly enhance user experiences. The maczzzzzzz/tang API provides a powerful set of Cognitive Actions that enable developers to generate images with precision and creativity. One such action is Generate Image with Mask, which allows for dynamic image creation using various customization options including aspect ratio, resolution, and prompt-driven generation. This article will guide you through the capabilities of this action and how to integrate it into your applications.

Prerequisites

Before diving into the implementation, ensure you have the following prerequisites:

  • An API key for accessing the Cognitive Actions platform.
  • A basic understanding of JSON and HTTP requests.
  • Familiarity with Python for executing the provided code examples.

Authentication typically involves passing your API key in the request headers, ensuring secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Mask

The Generate Image with Mask action allows you to create images using an input mask. This action supports both image-to-image and inpainting modes, providing flexibility in how images are generated. You can customize various parameters such as aspect ratio, resolution, and even use LoRA weights for advanced image manipulation.

Input

This action requires a specific input schema, primarily focused on the prompt. Here are the required and optional fields:

  • Required:
    • prompt: A string that describes the desired image (e.g., "in the style of tang, 2d cartoon drawing, orangutan eating pancakes on a table").
  • Optional:
    • mask: URI for an image mask used in inpainting mode.
    • seed: Random seed for reproducibility.
    • image: URI for an input image.
    • width: Width of the generated image in pixels (256 to 1440).
    • height: Height of the generated image in pixels (256 to 1440).
    • outputCount: Number of images to generate (default is 1).
    • inferenceModel: Model used for inference (options: "dev" or "schnell").
    • promptIntensity: Strength of the prompt (default is 0.8).
    • imageAspectRatio: Aspect ratio for the generated image (default is "1:1").
    • guidanceIntensity: Scale for the diffusion process (default is 3).
    • And several others for fine-tuning your image generation.

Here is an example input JSON payload:

{
  "prompt": "in the style of tang, 2d cartoon drawing, orangutan eating pancakes on a table",
  "outputCount": 1,
  "inferenceModel": "dev",
  "promptIntensity": 0.8,
  "imageAspectRatio": "1:1",
  "guidanceIntensity": 3.5,
  "imageOutputFormat": "webp",
  "mainLoraIntensity": 1,
  "imageOutputQuality": 90,
  "inferenceStepCount": 28,
  "additionalLoraIntensity": 1
}

Output

Upon successfully executing the action, you will receive a response containing the generated image URL. Here’s an example of what the output might look like:

[
  "https://assets.cognitiveactions.com/invocations/3171caf6-ab42-499d-ac72-9944f35c8a18/68d00ab8-b0ca-4e03-bcc2-23eabc92279e.webp"
]

This URL points to the newly created image, ready for use in your application.

Conceptual Usage Example (Python)

Below is a conceptual Python snippet demonstrating how to invoke the Generate Image with Mask action:

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 = "2f215f12-e7c9-44db-a6e4-7af8046a4396"  # Action ID for Generate Image with Mask

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "in the style of tang, 2d cartoon drawing, orangutan eating pancakes on a table",
    "outputCount": 1,
    "inferenceModel": "dev",
    "promptIntensity": 0.8,
    "imageAspectRatio": "1:1",
    "guidanceIntensity": 3.5,
    "imageOutputFormat": "webp",
    "mainLoraIntensity": 1,
    "imageOutputQuality": 90,
    "inferenceStepCount": 28,
    "additionalLoraIntensity": 1
}

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, you set your API key, specify the action ID, and construct the input payload as required by the action. The response is then printed, showing the generated image URL.

Conclusion

The Generate Image with Mask action from the maczzzzzzz/tang API empowers developers to create stunning visual content with ease. By leveraging its customizable parameters, you can cater to various artistic and graphical needs. Whether you aim to enhance your application’s aesthetic appeal or provide unique user-generated content, integrating this action opens up a world of possibilities. Explore its potential and consider how it can elevate your next project!

← Back to All Articles