Generate Stunning Images with the "marcodemutiis/belieber" Cognitive Action

23 Apr 2025
Generate Stunning Images with the "marcodemutiis/belieber" Cognitive Action

In the realm of machine learning, image generation has become an exciting frontier for developers and creators alike. The "marcodemutiis/belieber" Cognitive Actions provide a powerful toolset for generating images based on textual prompts using advanced LoRA models. This article will guide you through the capabilities of the "Generate Image from Prompt" action, exploring its features and how to integrate it into your applications.

Prerequisites

Before you can start using the Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic understanding of how to make API requests, particularly with JSON payloads.

Authentication typically works by passing your API key in the request headers, ensuring secure access to the action endpoints.

Cognitive Actions Overview

Generate Image from Prompt

The Generate Image from Prompt action is designed to create images based on user-defined prompts. This action supports various features like inpainting, custom aspect ratios, and fast generation modes, allowing for enhanced image quality and speed.

Input

The action requires a JSON payload structured according to the following schema:

{
  "prompt": "A belieberTOK person lost in the forest at night but he is happy and smiles at the camera",
  "goFast": false,
  "loraScale": 1,
  "numOutputs": 4,
  "guidanceScale": 3,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "png",
  "numInferenceSteps": 28
}

Required Fields:

  • prompt: Mandatory field where you specify the text prompt for image generation.

Optional Fields:

  • goFast: (boolean) Enables faster predictions.
  • loraScale: (number) Adjusts the intensity of the main LoRA application.
  • numOutputs: (integer) Number of images to generate (1 to 4).
  • guidanceScale: (number) Influences guidance during generation.
  • outputQuality: (integer) Quality setting for output images (0 to 100).
  • extraLoraScale: (number) Adjusts the intensity of additional LoRA weights.
  • inferenceModel: (string) Selects the inference model.
  • promptStrength: (number) Determines the influence of the prompt in image transformations.
  • imageMegapixels: (string) Defines the approximate megapixel count.
  • imageAspectRatio: (string) Sets the aspect ratio for the generated image.
  • imageOutputFormat: (string) Output format of the generated images.
  • numInferenceSteps: (integer) Total number of denoising steps during generation.

Output

The action typically returns an array of image URLs. Here's an example of the output you might receive:

[
  "https://assets.cognitiveactions.com/invocations/b7cbfba0-75d3-45de-89a4-5c7426734c48/696d7dde-ee9c-46e1-bdf7-031ad4d9dc55.png",
  "https://assets.cognitiveactions.com/invocations/b7cbfba0-75d3-45de-89a4-5c7426734c48/b575ad2c-63eb-4de8-89f0-485ef341a441.png",
  "https://assets.cognitiveactions.com/invocations/b7cbfba0-75d3-45de-89a4-5c7426734c48/bac408fc-dff1-4e51-9a71-76194313dcbf.png",
  "https://assets.cognitiveactions.com/invocations/b7cbfba0-75d3-45de-89a4-5c7426734c48/c45aee5f-a3db-4de1-8911-6f551259710b.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet showing how you might call the Generate Image from Prompt 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 = "29956955-7435-45ac-9456-30a92580be21"  # Action ID for Generate Image from Prompt

# Construct the input payload based on the action's requirements
payload = {
    "goFast": False,
    "prompt": "A belieberTOK person lost in the forest at night but he is happy and smiles at the camera",
    "loraScale": 1,
    "numOutputs": 4,
    "guidanceScale": 3,
    "outputQuality": 80,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageMegapixels": "1",
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "png",
    "numInferenceSteps": 28
}

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 and the endpoint URL with your actual details.
  • The action_id is set to the ID of the Generate Image from Prompt action.
  • The payload is constructed using the required and optional fields as specified in the action schema.

Conclusion

The Generate Image from Prompt action in the "marcodemutiis/belieber" Cognitive Actions provides an exceptional opportunity for developers to create unique images from textual descriptions. With various customization options, this action can be seamlessly integrated into applications for artistic, illustrative, or functional use cases. Start experimenting with it today to unlock the creative potential of AI-driven image generation!

← Back to All Articles