Generate Stunning Images with the nic-seo/miya-char Cognitive Actions

22 Apr 2025
Generate Stunning Images with the nic-seo/miya-char Cognitive Actions

In the realm of AI and machine learning, image generation has rapidly evolved, allowing developers to create visually compelling content based on textual descriptions. The nic-seo/miya-char Cognitive Actions offer powerful capabilities to generate images from prompts, providing developers with tools to transform concepts into visuals. Utilizing these pre-built actions can greatly enhance applications focused on creative content, marketing, and more, by streamlining the image creation process.

Prerequisites

To get started with the nic-seo/miya-char Cognitive Actions, you will need:

  • An API key to authenticate requests to the Cognitive Actions platform.
  • A basic understanding of JSON format for constructing input payloads.

Authentication typically involves including your API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Image with Mask and Prompt

This action generates images using a specific prompt and image mask, supporting image-to-image transformations and inpainting mode. It allows for customization of image properties like aspect ratio and resolution, and uses models optimized for either detail or speed.

Input

The required input schema for this action is as follows:

{
  "prompt": "Your descriptive text here",
  "mask": "http://example.com/mask.png", // optional
  "image": "http://example.com/image.png", // optional
  "model": "dev", // optional, default is "dev"
  "width": 512, // optional
  "height": 512, // optional
  "imageFormat": "webp", // optional, default is "webp"
  "imageQuality": 90, // optional, default is 80
  "numberOfOutputs": 1, // optional, default is 1
  "promptInfluence": 0.8, // optional, default is 0.8
  "imageAspectRatio": "16:9" // optional, default is "1:1"
}

Example Input:

{
  "model": "dev",
  "prompt": "San runs around in a green field of wildflowers with her arms outstretched like an airplane and her feet kicking back behind her, a look of freedom and joy on her face.",
  "imageFormat": "webp",
  "imageQuality": 90,
  "numberOfOutputs": 2,
  "promptInfluence": 0.8,
  "imageAspectRatio": "16:9"
}

Output

Upon successful execution, the action returns an array of URLs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/c9323492-58fb-4948-88a2-a4c92d0dcd71/e740ee43-9209-430a-97b7-c859808e090d.webp",
  "https://assets.cognitiveactions.com/invocations/c9323492-58fb-4948-88a2-a4c92d0dcd71/e2c525b1-1d79-4c27-a9dc-7c6b32186f82.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet to demonstrate how you might call this 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 = "be189cc8-5a7a-4bfc-a37c-f7b5cda108f0"  # Action ID for Generate Image with Mask and Prompt

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "San runs around in a green field of wildflowers with her arms outstretched like an airplane and her feet kicking back behind her, a look of freedom and joy on her face.",
    "imageFormat": "webp",
    "imageQuality": 90,
    "numberOfOutputs": 2,
    "promptInfluence": 0.8,
    "imageAspectRatio": "16:9"
}

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 payload variable is structured according to the required input schema for the action.

Conclusion

The nic-seo/miya-char Cognitive Actions provide developers with robust tools to generate images based on descriptive prompts. With options for customization and flexibility in output formats, these actions can significantly enhance applications that require creative visuals. Next steps could include experimenting with different prompts, image aspects, and quality settings to find the optimal configurations for your specific use cases. Happy coding!

← Back to All Articles