Generate Stunning Images with Cognitive Actions: A Guide to the mainemarty/marty API

23 Apr 2025
Generate Stunning Images with Cognitive Actions: A Guide to the mainemarty/marty API

In the world of artificial intelligence, image generation has become a fascinating frontier. With the mainemarty/marty API, developers can leverage powerful Cognitive Actions to create custom images through inpainting techniques. This API offers a range of options that allow you to specify various aspects of the images, from dimensions to model selection, enabling you to produce unique and creative outputs effortlessly.

Prerequisites

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

  • An API key for the mainemarty/marty Cognitive Actions platform.
  • Basic understanding of RESTful APIs and JSON format.
  • Familiarity with Python for implementing the provided conceptual 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 Inpainting

Description:
This action creates a generated image using inpainting techniques, allowing for customization of various image aspects such as width, height, and aspect ratio. You can choose between 'dev' and 'schnell' models for varying inference speeds.

Category: image-generation

Input

The input schema for this action requires the following fields:

  • prompt (required): A descriptive text prompt for image generation (e.g., "Marty as a zombie clown").
  • model (optional): Select between "dev" (default) for optimal performance or "schnell" for faster but less detailed results.
  • width (optional): Specified image width (256-1440) applicable only with a custom aspect ratio.
  • height (optional): Specified image height (256-1440) applicable only with a custom aspect ratio.
  • totalOutputs (optional): Number of outputs to produce (1-4).
  • imageAspectRatio (optional): Defines the aspect ratio of the image (default is "1:1").
  • imageOutputFormat (optional): Format of the output images; options include "webp", "jpg", or "png".
  • imageOutputQuality (optional): Sets the quality of the output from 0 to 100.
  • Additional fields such as seed, enableFastMode, and various LoRA parameters allow further customization.

Example Input:

{
  "model": "dev",
  "prompt": "Marty as a zombie clown",
  "totalOutputs": 1,
  "loraWeightScale": 1,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "imageOutputQuality": 90,
  "inferenceStepCount": 28,
  "additionalLoraScale": 1,
  "img2imgPromptStrength": 0.8,
  "diffusionGuidanceScale": 3.5
}

Output

The output of this action typically returns a URL to the generated image. For example, an output could look like:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e1f1ef6b-d398-4768-a9c6-a1988de95bb7/7a64b910-cc05-44d0-a5de-952960ddb2e4.webp"
]

Conceptual Usage Example (Python)

Here's how you might call this 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 = "66719a3c-33c0-462f-b23c-4a4562cf70d0"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "Marty as a zombie clown",
    "totalOutputs": 1,
    "loraWeightScale": 1,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "imageOutputQuality": 90,
    "inferenceStepCount": 28,
    "additionalLoraScale": 1,
    "img2imgPromptStrength": 0.8,
    "diffusionGuidanceScale": 3.5
}

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 YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key, and be sure to adjust the endpoint URL if necessary. The input payload is structured based on the action's requirements, ensuring a seamless call to the Cognitive Actions API.

Conclusion

The mainemarty/marty Cognitive Actions offer developers a powerful and flexible way to generate images using advanced inpainting techniques. By utilizing the provided parameters, you can create unique and tailored images for your applications. Whether you are looking to enhance artistic projects or automate creative workflows, these Cognitive Actions are a valuable tool in your development arsenal. Start experimenting today and unlock the potential of AI-driven image generation!

← Back to All Articles