Unlocking Image Generation with the mayoita/max-cvg Cognitive Actions

22 Apr 2025
Unlocking Image Generation with the mayoita/max-cvg Cognitive Actions

In the evolving landscape of artificial intelligence, the ability to generate and manipulate images has become a cornerstone for developers looking to enhance their applications. The mayoita/max-cvg specification provides a powerful Cognitive Action that allows developers to generate images using advanced models. With options for image inpainting, aspect ratio adjustments, and various output settings, these pre-built actions offer an efficient way to integrate cutting-edge image generation capabilities into your applications.

Prerequisites

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

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with JSON structure, as the input and output data will be formatted in JSON.
  • Basic understanding of RESTful APIs and Python programming would be beneficial for implementing the examples.

Authentication

Authentication typically involves passing your API key in the request headers. This secures your requests and allows you to access the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with CVG Model

The Generate Image with CVG Model action is designed to create images based on user-defined prompts. The action supports various configurations, allowing for detailed customization such as aspect ratios, image quality, and even image inpainting.

Input

The input for this action requires a JSON object and includes the following fields:

  • prompt (required): The description of the image to be generated.
  • mask (optional): An image mask for inpainting mode.
  • seed (optional): A random seed for reproducibility.
  • model (optional): Choose between "dev" and "schnell" models.
  • width (optional): Width of the generated image (if using custom aspect ratio).
  • height (optional): Height of the generated image (if using custom aspect ratio).
  • goFast (optional): Speed optimization flag.
  • outputCount (optional): Number of outputs to generate (1 to 4).
  • imageQuality (optional): Quality of the saved output images (0 to 100).
  • loraIntensity (optional): Intensity of the main LoRA application.
  • additionalLora (optional): Load extra LoRA weights from external sources.
  • externalWeights (optional): Load additional model weights.
  • imageResolution (optional): Approximate number of megapixels.
  • promptIntensity (optional): Strength of the prompt when using img2img.
  • imageAspectRatio (optional): Specifies the aspect ratio of the generated image.
  • guidanceIntensity (optional): Scale for the diffusion process.
  • imageOutputFormat (optional): Format of the output images (webp, jpg, png).
  • inferenceStepCount (optional): Number of denoising steps.
  • safetyCheckerDisabled (optional): Disable the safety checker.
  • additionalLoraIntensity (optional): Intensity of any extra LoRA application.

Example Input:

{
  "model": "dev",
  "prompt": "close up of cvg, the woman stands in an empty subway train, holding on to the pole with one hand and holding a briefcase with the other. she is wearing a coat, rays of light, haze, shot on a mobile phone, amateur low resolution photo, overexposed, the dirty window is revealing a brutalist apartment complex, late autumn, close up of her face",
  "outputCount": 1,
  "imageQuality": 90,
  "loraIntensity": 1,
  "promptIntensity": 0.8,
  "imageAspectRatio": "1:1",
  "guidanceIntensity": 3.14,
  "imageOutputFormat": "webp",
  "inferenceStepCount": 28,
  "additionalLoraIntensity": 1
}

Output

The output of this action will be an array of generated image URLs, which can be accessed and displayed in your application.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/d128118a-2b1e-45dd-80e1-6cded87939e5/3c219e79-5e32-4aa5-b263-2755ba608fae.webp"
]

Conceptual Usage Example (Python)

Here's an example of how you might call the Generate Image with CVG Model 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 = "c9d695e9-93e9-48a9-a091-bffc054c06dd"  # Action ID for Generate Image with CVG Model

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "close up of cvg, the woman stands in an empty subway train, holding on to the pole with one hand and holding a briefcase with the other. she is wearing a coat, rays of light, haze, shot on a mobile phone, amateur low resolution photo, overexposed, the dirty window is revealing a brutalist apartment complex, late autumn, close up of her face",
    "outputCount": 1,
    "imageQuality": 90,
    "loraIntensity": 1,
    "promptIntensity": 0.8,
    "imageAspectRatio": "1:1",
    "guidanceIntensity": 3.14,
    "imageOutputFormat": "webp",
    "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 code snippet, replace the COGNITIVE_ACTIONS_API_KEY and COGNITIVE_ACTIONS_EXECUTE_URL with your actual API key and endpoint. The action_id is set for the image generation action, and the input payload is structured according to the action's requirements.

Conclusion

The mayoita/max-cvg Cognitive Actions provide developers with a powerful toolset for generating custom images tailored to specific prompts. By leveraging these pre-built actions, you can enhance your applications with advanced image creation capabilities, enabling a wide range of use cases from creative content generation to personalized user experiences. Start integrating these actions today and unlock the potential of AI-driven image generation in your projects!

← Back to All Articles