Unlocking Image Generation with the annaicon/mani Cognitive Actions

23 Apr 2025
Unlocking Image Generation with the annaicon/mani Cognitive Actions

In the world of AI and image generation, the annaicon/mani spec offers powerful Cognitive Actions that enable developers to create custom images through advanced techniques like inpainting and image-to-image transformations. With a variety of customizable settings, these pre-built actions allow you to generate high-quality images tailored to your specifications, making it easier to bring your creative ideas to life.

Prerequisites

Before diving into using the annaicon/mani Cognitive Actions, make sure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic familiarity with making API calls and handling JSON payloads.
  • A suitable environment for executing Python code, such as a local setup with the requests library installed.

Authentication is typically handled by including your API key in the request headers, allowing you to securely access the actions.

Cognitive Actions Overview

Generate Image with Inpainting and Customization

This action facilitates the generation of images using a combination of image-to-image and inpainting modes. Developers can customize settings such as dimensions, aspect ratio, and output quality, making it versatile for various design needs.

Input

The input schema for this action requires a prompt and allows for several optional fields. Below is a breakdown of the required and optional inputs:

  • Required:
    • prompt: A detailed text description guiding the image generation.
  • Optional:
    • mask: Image mask for inpainting mode.
    • seed: An integer for consistent random results.
    • image: Input image for transformations.
    • width: Width of the generated image (256 to 1440).
    • height: Height of the generated image (256 to 1440).
    • loadWeights, mainLoraScale, outputQuality, enableFastMode, inferenceModel, inferenceSteps, promptStrength, imageMegapixels, numberOfOutputs, imageAspectRatio, imageOutputFormat, additionalLoraScale, diffusionGuidanceScale, deactivateSafetyChecker.

Here's an example JSON payload for invoking the action:

{
  "prompt": "mani a lean, athletic man with a well-defined but compact physique sits confidently in a photorealistic business setting. mani has a lightly tanned complexion, a shaved head, and a clean-shaven face. His expression is warm and confident, with a friendly smile.",
  "mainLoraScale": 1,
  "outputQuality": 80,
  "enableFastMode": false,
  "inferenceModel": "dev",
  "inferenceSteps": 28,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "additionalLoraScale": 1,
  "diffusionGuidanceScale": 3
}

Output

The action typically returns an array of URLs pointing to the generated images. Here is an example output:

[
  "https://assets.cognitiveactions.com/invocations/247603d9-06fe-4d0d-bd6f-6f75937d31ab/dcafe0ad-4dbe-4007-956c-6450f41e8245.webp"
]

Conceptual Usage Example (Python)

To utilize this action, you can structure your Python code as follows:

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 = "9918cda8-8346-45eb-9093-be49b8e63ef5"  # Action ID for Generate Image with Inpainting and Customization

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "mani a lean, athletic man with a well-defined but compact physique sits confidently in a photorealistic business setting. mani has a lightly tanned complexion, a shaved head, and a clean-shaven face. His expression is warm and confident, with a friendly smile.",
    "mainLoraScale": 1,
    "outputQuality": 80,
    "enableFastMode": false,
    "inferenceModel": "dev",
    "inferenceSteps": 28,
    "promptStrength": 0.8,
    "imageMegapixels": "1",
    "numberOfOutputs": 1,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "additionalLoraScale": 1,
    "diffusionGuidanceScale": 3
}

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:

  • Replace the placeholder for COGNITIVE_ACTIONS_API_KEY with your actual key.
  • The payload is constructed based on the input schema requirements.
  • The action ID is set according to the action you are executing.

Conclusion

The annaicon/mani Cognitive Actions provide powerful tools for generating images with customization options that suit your specific needs. By integrating these actions into your applications, you can streamline the creative process and produce high-quality visuals efficiently. Whether you are developing a game, artwork, or any content requiring imagery, these actions can significantly enhance your capabilities. Explore various configurations and experiment with different prompts to unlock the full potential of image generation!

← Back to All Articles