Enhance Your Applications with Image Generation Using the Temptrain Cognitive Actions

24 Apr 2025
Enhance Your Applications with Image Generation Using the Temptrain Cognitive Actions

In the digital age, the ability to generate unique and compelling images programmatically can greatly enhance user engagement and creativity in applications. The Temptrain Cognitive Actions API provides developers with powerful tools for image generation, specifically through advanced inpainting and refinement techniques. These pre-built actions not only streamline the development process but also allow for a high degree of customization, making it easier to create unique content tailored to specific needs.

Prerequisites

Before you begin using the Temptrain Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic knowledge of JSON and familiarity with making HTTP requests.

Authentication typically involves passing your API key in the request headers, allowing you to securely access the functionality provided by the API.

Cognitive Actions Overview

Generate Image with Inpainting and Refinement

The Generate Image with Inpainting and Refinement action is designed to create images using sophisticated inpainting techniques. This action allows developers to refine images by adjusting various parameters such as resolution, output quantity, and guidance scales, ensuring high-quality and unique generated content.

Input

The input for this action is structured as follows:

{
  "mask": "https://example.com/mask.png",
  "seed": 12345,
  "image": "https://example.com/input-image.png",
  "width": 1024,
  "height": 1024,
  "prompt": "illustration of JSPR dog in cyberpunk style surrounded by city",
  "loraWeights": "https://example.com/lora-weights.json",
  "scheduleType": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "refinementSteps": 10,
  "refinementStyle": "no_refiner",
  "highNoiseFraction": 0.8,
  "loraScalingFactor": 0.6,
  "disableSafetyChecker": false,
  "numberOfInferenceSteps": 50
}

Required Fields:

  • prompt: Text describing the desired content or style of the generated image.
  • width: Width of the output image in pixels (default: 1024).
  • height: Height of the output image in pixels (default: 1024).
  • numberOfOutputs: Number of images to generate (1-4; default: 1).

Optional Fields:

  • mask: URI of the input mask for inpainting.
  • seed: Random seed for reproducibility.
  • scheduleType: Type of scheduler algorithm (defaults to 'K_EULER').
  • guidanceScale: Scale factor for guidance (1-50; default: 7.5).
  • applyWatermark: Whether to apply a watermark (default: true).
  • negativePrompt: Text to discourage certain content.
  • promptStrength: Influence of the prompt (0-1; default: 0.8).
  • refinementSteps: Number of refinement steps.
  • refinementStyle: Style of refinement to apply.
  • highNoiseFraction: Fraction of noise for refinement.
  • loraScalingFactor: Scaling factor for LoRA application.
  • disableSafetyChecker: Option to disable the safety checker.
  • numberOfInferenceSteps: Number of denoising steps.

Output

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

[
  "https://assets.cognitiveactions.com/invocations/b8c14827-6121-4448-a0d0-a9fb617f4e28/ed3759ed-7d22-4690-bdbb-9a28297f5c5c.png"
]

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

Conceptual Usage Example (Python)

Here’s how a developer might invoke 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 = "3294480d-8689-48dc-9595-6a88b610c74b" # Action ID for Generate Image with Inpainting and Refinement

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "illustration of JSPR dog in cyberpunk style surrounded by city",
    "scheduleType": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": true,
    "negativePrompt": "",
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "refinementStyle": "no_refiner",
    "highNoiseFraction": 0.8,
    "loraScalingFactor": 0.6,
    "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 code snippet, replace the placeholder API key and endpoint with your actual credentials. The payload is constructed according to the action's input schema, ensuring that all required fields are included. The response from the API will include the URL of the generated image.

Conclusion

The Temptrain Cognitive Actions provide a robust framework for image generation, enabling developers to create visually stunning and unique content with minimal effort. By leveraging the power of inpainting and refinement, you can enhance user experiences in your applications. Consider exploring various use cases, such as personalized content creation, marketing materials, or even game assets, to fully utilize these capabilities in your projects. Happy coding!

← Back to All Articles