Unlocking Creative Potential: Image Generation with f1ameglory/moa Cognitive Actions

24 Apr 2025
Unlocking Creative Potential: Image Generation with f1ameglory/moa Cognitive Actions

Cognitive Actions in the f1ameglory/moa specification offer developers a powerful way to generate images using advanced techniques like inpainting. The actions provided allow for the customization of various aspects, enabling efficient integration into applications that require dynamic image creation. This article will guide you through the specific action available, showcasing its capabilities and providing practical examples to help you integrate it seamlessly into your projects.

Prerequisites

Before diving into the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which you'll use for authentication.
  • Familiarity with sending HTTP requests and handling JSON data in your preferred programming language, as you'll be constructing API calls to execute the actions.

Authentication typically involves including your API key in the request headers.

Cognitive Actions Overview

Generate Image with Inpainting

Description:
This action allows you to create an image using inpainting techniques. You can customize various parameters, such as model selection, image dimensions, aspect ratio, and output format. It supports faster image generation and the integration of LoRA weights for enhanced effects.

  • Category: Image Generation

Input

The input for this action consists of several required and optional fields. Below is a breakdown of the input schema:

  • Required:
    • prompt: A text prompt guiding the image generation.
  • Optional:
    • mask: URI to an image mask for inpainting.
    • seed: Integer for random number generation.
    • image: URI to an input image for transformation.
    • model: Choose between "dev" or "schnell".
    • width & height: Dimensions for the generated image (applicable for custom aspect ratios).
    • isFast: Boolean to enable faster predictions.
    • outputFormat: Format for the generated images (webp, jpg, png).
    • guidanceScale: Number to influence image generation detail.
    • loraIntensity: Adjust the strength of LoRA application.
    • additionalLora: Path to additional LoRA weights.
    • promptStrength: Strength when using image-to-image transformations.
    • numberOfOutputs: Number of images to generate.
    • imageAspectRatio: Aspect ratio of the generated image.
    • numberInferenceSteps: Count of denoising steps.
    • isSafetyCheckerDisabled: Option to disable safety checks.

Example Input:

{
  "model": "dev",
  "isFast": false,
  "prompt": "Hyperrealistic portrait of an alien princess moa_basic",
  "outputFormat": "webp",
  "guidanceScale": 3,
  "loraIntensity": 1,
  "outputQuality": 80,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "imageAspectRatio": "16:9",
  "numberInferenceSteps": 28,
  "additionalLoraIntensity": 1
}

Output

The output from this action typically returns a list of URLs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/142ca474-ba64-4b8d-a69f-e7ffff4ade2f/c0de4b69-834f-4225-b495-1816e2cd984a.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call this 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 = "4710fee9-892a-4242-9912-fdb994d85921"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "isFast": False,
    "prompt": "Hyperrealistic portrait of an alien princess moa_basic",
    "outputFormat": "webp",
    "guidanceScale": 3,
    "loraIntensity": 1,
    "outputQuality": 80,
    "promptStrength": 0.8,
    "imageMegapixels": "1",
    "numberOfOutputs": 1,
    "imageAspectRatio": "16:9",
    "numberInferenceSteps": 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 Python code snippet, you replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID is set for the "Generate Image with Inpainting" action, and the input payload is structured according to the requirements outlined above. The response will contain URLs to the generated images.

Conclusion

The f1ameglory/moa Cognitive Actions provide a robust solution for developers looking to integrate image generation capabilities into their applications. With features like inpainting, customizable parameters, and support for advanced models, these actions can help create stunning visuals quickly and efficiently. Consider experimenting with different prompts and settings to see how you can leverage this power in your projects!

← Back to All Articles