Generate Stunning Images with apurv2311/starperformer Cognitive Actions

22 Apr 2025
Generate Stunning Images with apurv2311/starperformer Cognitive Actions

In today's rapidly evolving digital landscape, the ability to generate visual content programmatically can significantly enhance applications across various domains. The apurv2311/starperformer API offers a powerful set of Cognitive Actions designed specifically for image generation. One of the standout features is the ability to create custom images using textual prompts and a variety of settings. This article will walk you through how to utilize the Generate Custom Images with LoRA action to bring your creative visions to life.

Prerequisites

Before getting started, ensure you have the following:

  • An API key for the Cognitive Actions platform, which is essential for authenticating your requests.
  • Familiarity with making HTTP requests and handling JSON payloads in your preferred programming language.

For authentication, you will typically pass your API key in the headers of your requests, allowing you to securely access the Cognitive Actions services.

Cognitive Actions Overview

Generate Custom Images with LoRA

The Generate Custom Images with LoRA action enables developers to generate images based on textual prompts. This action supports various configurations, including different models, output formats, and quality settings. It is particularly useful for creating unique visuals that can enhance user engagement in applications.

Input

The action requires a JSON payload with the following fields (not all fields are required, but the prompt is mandatory):

  • prompt (string): The text that guides the image generation. For example: "The person in the photos is benchpressing 100 kg".
  • model (string): Specify the model for inference, options include "dev" or "schnell" (default: "dev").
  • fastMode (boolean): Enable for speed-optimized image generation (default: false).
  • outputCount (integer): Number of images to generate (ranging from 1 to 4, default: 1).
  • imageQuality (integer): Quality of the output images, ranging from 0 to 100 (default: 80).
  • loraStrength (number): Adjusts the influence of the LoRA module on the output (default: 1).
  • imageAspectRatio (string): Select the aspect ratio for the generated image (default: "1:1").
  • imageOutputFormat (string): Choose the output format for images ("webp", "jpg", or "png").

Here is an example of a complete input payload:

{
  "model": "dev",
  "prompt": "The person in the photos is benchpressing 100 kg",
  "fastMode": false,
  "outputCount": 1,
  "imageQuality": 80,
  "loraStrength": 1,
  "imageResolution": "1",
  "promptIntensity": 0.8,
  "guidanceStrength": 3,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "extraLoraIntensity": 1,
  "inferenceStepCount": 28
}

Output

Upon successful execution, the action returns a URL to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/031c4d72-9db7-40e0-bb8e-d6da33dfb581/651b4130-ad18-4368-b34f-a67e448c37eb.webp"
]

This URL points to the generated image, which can be used directly in your applications.

Conceptual Usage Example (Python)

Here’s how you might call the Generate Custom Images with LoRA 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 = "e1207805-8e8d-4cbc-a36b-e54e950783bc"  # Action ID for Generate Custom Images with LoRA

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "The person in the photos is benchpressing 100 kg",
    "fastMode": False,
    "outputCount": 1,
    "imageQuality": 80,
    "loraStrength": 1,
    "imageResolution": "1",
    "promptIntensity": 0.8,
    "guidanceStrength": 3,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "extraLoraIntensity": 1,
    "inferenceStepCount": 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 code snippet, replace your API key and endpoint with the correct values. The input payload is structured according to the action's requirements, and the response is handled gracefully to capture any errors.

Conclusion

The Generate Custom Images with LoRA action from the apurv2311/starperformer API provides a robust way to create stunning visuals based on textual descriptions. By leveraging this action, developers can enhance their applications with unique and engaging content.

Now that you're familiar with how to use this Cognitive Action, consider experimenting with different prompts and configurations to see the full potential of image generation in your projects!

← Back to All Articles