Create Stunning Inpainted Images with tstramer/tron-legacy-diffusion Cognitive Actions

22 Apr 2025
Create Stunning Inpainted Images with tstramer/tron-legacy-diffusion Cognitive Actions

In today's digital landscape, the ability to generate and manipulate images through AI is transforming the way developers create visual content. The tstramer/tron-legacy-diffusion API offers powerful Cognitive Actions that enable developers to produce stunning inpainted images. This API harnesses the capabilities of the Tron Legacy Diffusion model, allowing you to generate images based on text prompts and optional initial images, as well as fine-tune the output using various parameters. By leveraging these pre-built actions, developers can save time and resources while enhancing their applications with advanced image generation features.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Basic understanding of making API calls and handling JSON data.
  • Conceptual familiarity with Python for executing the actions.

To authenticate with the API, you typically pass your API key in the request headers.

Cognitive Actions Overview

Generate Inpainted Images

The Generate Inpainted Images action allows you to produce images by filling in specified areas based on a text prompt and an optional initial image. This action is categorized under image-generation and offers various configurable parameters to influence the final output.

Input

The input for this action is structured as follows:

{
  "mask": "string (optional)",
  "seed": "integer (optional)",
  "width": "integer (default: 512)",
  "height": "integer (default: 512)",
  "prompt": "string (required)",
  "scheduler": "string (default: K-LMS)",
  "initialImage": "string (optional)",
  "guidanceScale": "number (default: 7.5)",
  "promptStrength": "number (default: 0.8)",
  "numberOfOutputs": "integer (default: 1)",
  "numberOfInferenceSteps": "integer (default: 50)"
}

Here’s a practical example of the JSON payload you would use to invoke this action:

{
  "width": 512,
  "height": 512,
  "prompt": "city landscape in the style of trnlgcy",
  "scheduler": "K-LMS",
  "guidanceScale": 7.5,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Output

Upon successfully executing the action, you can expect an output similar to the following:

[
  "https://assets.cognitiveactions.com/invocations/e721477d-f654-4c4c-af67-381f436fe602/1d61a4fe-9059-43b9-9663-10da6250f053.png"
]

This output consists of a URL pointing to the generated image, which you can then display or manipulate further in your application.

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to call the Generate Inpainted Images 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 = "03f3f473-8d3f-4e21-9e71-86e9af4b9aa2"  # Action ID for Generate Inpainted Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 512,
    "height": 512,
    "prompt": "city landscape in the style of trnlgcy",
    "scheduler": "K-LMS",
    "guidanceScale": 7.5,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 50
}

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, you replace the placeholder for the API key and send a request to a hypothetical endpoint. The action ID for generating inpainted images is included in the request, along with the structured input payload.

Conclusion

The tstramer/tron-legacy-diffusion Cognitive Actions provide developers with a robust toolkit for image generation. By utilizing the Generate Inpainted Images action, you can create visually appealing images tailored to specific prompts, enhancing the user experience in your applications. As a next step, consider experimenting with different prompt configurations and parameters to explore the full potential of this powerful API. Happy coding!

← Back to All Articles