Enhance Your Applications with banta2000/mytestmodel: Image Generation Made Easy

22 Apr 2025
Enhance Your Applications with banta2000/mytestmodel: Image Generation Made Easy

The banta2000/mytestmodel API offers a powerful Cognitive Action designed for developers looking to integrate advanced image generation capabilities into their applications. With features such as inpainting, custom dimensions, and fast generation mode, this model provides a flexible approach to creating high-quality images based on user-defined prompts. By leveraging these pre-built actions, developers can save time and effort, allowing them to focus on building innovative solutions.

Prerequisites

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

  • An API key to access the Cognitive Actions platform.
  • Familiarity with JSON format for constructing requests.
  • Basic knowledge of making HTTP requests.

Authentication typically involves passing your API key in the request headers. This is crucial for ensuring secure access to the API.

Cognitive Actions Overview

Generate Image with Inpainting and Fast Mode Options

The Generate Image with Inpainting and Fast Mode Options action allows developers to create images from a text prompt, with various options to customize the output. This includes support for inpainting, custom dimensions, fast generation, and various output formats.

Input

The input schema for this action requires the following fields:

  • prompt (required): The text prompt to generate the image. Example: "portrait photo of MANULE as a male flying a fighter jet"
  • mask (optional): URL for an image mask used in inpainting mode.
  • seed (optional): Random seed for reproducible generation.
  • image (optional): Input image for image-to-image or inpainting mode.
  • width (optional): Width of the generated image (if aspect ratio is set to custom).
  • height (optional): Height of the generated image (if aspect ratio is set to custom).
  • goFast (optional): Boolean to enable fast processing.
  • loraScale (optional): Scale for LoRA application (default is 1).
  • numOutputs (optional): Number of images to generate (default is 1).
  • guidanceScale (optional): Scale for the diffusion process (default is 3).
  • outputQuality (optional): Quality of the output images (default is 80).
  • inferenceModel (optional): Choose between "dev" and "schnell".
  • promptStrength (optional): Strength of the prompt when using image-to-image.
  • imageAspectRatio (optional): Specifies the aspect ratio of the generated image.
  • imageOutputFormat (optional): Format for saving output images.
  • numInferenceSteps (optional): Number of denoising steps (default is 28).
  • additionalLoraScale (optional): Additional scaling for LoRA application.

Example input JSON:

{
  "prompt": "portrait photo of MANULE as a male flying a fighter jet",
  "loraScale": 1,
  "numOutputs": 1,
  "guidanceScale": 3.5,
  "outputQuality": 80,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "numInferenceSteps": 28,
  "additionalLoraScale": 0.8
}

Output

The output of this action typically returns a URL to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/9a983ed1-56ab-4c08-b7eb-5a9218d8e99f/ddd6201d-bac2-4478-b157-db773916a51e.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 = "a20a968f-0397-4c84-b662-7370bf40e474" # Action ID for Generate Image with Inpainting and Fast Mode Options

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "portrait photo of MANULE as a male flying a fighter jet",
    "loraScale": 1,
    "numOutputs": 1,
    "guidanceScale": 3.5,
    "outputQuality": 80,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "numInferenceSteps": 28,
    "additionalLoraScale": 0.8
}

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 with your actual API key. The payload variable contains the input structured according to the action's requirements. The response will contain the URL of the generated image.

Conclusion

The banta2000/mytestmodel Cognitive Actions provide developers with a robust tool for generating images through flexible prompts and settings. By using these capabilities, you can enhance your applications with rich visual content tailored to user specifications. Consider exploring additional use cases, such as integrating real-time image generation into creative applications or content management systems. Happy coding!

← Back to All Articles