Generate Stunning Images with Cognitive Actions in jhona199612/stg

23 Apr 2025
Generate Stunning Images with Cognitive Actions in jhona199612/stg

In the world of digital creativity, the ability to generate images programmatically has become increasingly important. The jhona199612/stg API offers powerful Cognitive Actions designed to create detailed images with customizable options. With these pre-built actions, developers can seamlessly integrate advanced image generation capabilities into their applications, streamlining processes and enhancing user experience.

Prerequisites

Before diving into the Cognitive Actions, there are a few prerequisites to keep in mind:

  • API Key: You will need an API key to interact with the Cognitive Actions platform.
  • Setup: Ensure that your development environment is ready to make HTTP requests (e.g., using libraries like requests in Python).

Authentication typically involves passing your API key in the headers of your requests, allowing secure access to the functionalities provided by the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows developers to create highly detailed images using inpainting mode. This powerful tool supports various models, enabling customizable settings such as prompt intensity, image aspect ratio, and guidance scale, making it an ideal choice for transforming visual content.

Input

The Input for this action is structured as follows:

  • prompt (required): A detailed description of the image you want to generate.
  • mask (optional): An image mask to specify areas for inpainting.
  • seed (optional): A random seed for reproducible results.
  • image (optional): An input image for image-to-image transformations.
  • model (optional): Choose between "dev" for detailed generation or "schnell" for faster processing.
  • width (optional): Width of the generated image (if applicable).
  • height (optional): Height of the generated image (if applicable).
  • aspectRatio (optional): Aspect ratio for the generated image.
  • outputFormat (optional): Format of the output images (e.g., "webp", "jpg", "png").
  • numberOfOutputs (optional): Number of images to generate.

Here’s an example of the input JSON payload:

{
  "model": "dev",
  "prompt": "Using the STG manual nail gun LoRA, generate a highly detailed image of the STG manual nail gun in a construction environment.",
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceValue": 3.5,
  "loraIntensity": 1,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 28,
  "additionalLoraIntensity": 1
}

Output

The Output of the action typically returns a URL to the generated image. For instance:

[
  "https://assets.cognitiveactions.com/invocations/1bcaaf4f-3b69-4909-bd31-712fbbfdfb20/ed8e7af9-7655-422a-838b-0e50201a8761.webp"
]

This URL can be used to access the generated image directly.

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to invoke the Generate Image with Inpainting 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 = "e8e165a8-1c36-42c9-9c98-4b2045d0be5d"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "Using the STG manual nail gun LoRA, generate a highly detailed image of the STG manual nail gun in a construction environment.",
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceValue": 3.5,
    "loraIntensity": 1,
    "outputQuality": 90,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is constructed according to the requirements of the action, and the response is handled to print the result or any errors encountered.

Conclusion

The Generate Image with Inpainting action within the jhona199612/stg API provides developers with a robust tool to create intricate images tailored to specific needs. By leveraging the customizable options available, you can enhance your applications with stunning visuals, paving the way for innovative user experiences.

To get started, simply implement the provided Python example, and explore the myriad of possibilities that image generation can offer in your own projects. Happy coding!

← Back to All Articles