Generate Stunning Images with the chenxwh/nova-t2i Cognitive Actions

24 Apr 2025
Generate Stunning Images with the chenxwh/nova-t2i Cognitive Actions

Creating visually compelling images has never been easier, thanks to the chenxwh/nova-t2i Cognitive Actions. These pre-built actions enable developers to harness the power of the NOVA model for efficient and diverse image generation. By leveraging autoregressive techniques without vector quantization, you can produce stunning visuals tailored to your specifications. This guide will walk you through the key capabilities of the "Generate Image with NOVA" action, helping you integrate this functionality into your applications seamlessly.

Prerequisites

Before diving into the implementation, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be used for authentication.
  • Familiarity with making HTTP requests and handling JSON data.

To authenticate your requests, you will typically include your API key in the headers of your HTTP calls.

Cognitive Actions Overview

Generate Image with NOVA

The Generate Image with NOVA action allows you to create high-quality images based on specific prompts. This action is categorized under image generation and is designed to facilitate zero-shot generation with state-of-the-art performance.

Input

The input schema for this action is structured as follows:

  • seed (optional): An integer to specify the random seed for reproducibility. If omitted, the seed will be randomized.
  • prompt (required): A string input that describes the desired content of the image. Default is "a shiba inu wearing a beret and black turtleneck."
  • guidanceScale (optional): A number between 1 and 10 that influences adherence to the prompt. Default is 5.
  • negativePrompt (optional): A string detailing undesirable elements to avoid in the output. Default includes phrases like "low quality, deformed, distorted, disfigured."
  • numberOfDiffusionSteps (optional): An integer indicating the total number of diffusion steps for refinement, ranging from 1 to 50. Default is 25.
  • numberOfInferenceSteps (optional): An integer for the total number of inference steps, affecting output resolution, ranging from 1 to 128. Default is 64.

Here’s an example of the JSON payload needed to invoke this action:

{
  "prompt": "a shiba inu wearing a beret and black turtleneck.",
  "guidanceScale": 5,
  "negativePrompt": "low quality, deformed, distorted, disfigured, fused fingers, bad anatomy, weird hand",
  "numberOfDiffusionSteps": 25,
  "numberOfInferenceSteps": 64
}

Output

When you successfully execute the action, it typically returns a URL pointing to the generated image. For example:

https://assets.cognitiveactions.com/invocations/03da34f4-3734-413f-82d3-839d17e78351/845cddae-1d8e-4c1a-9800-b9395e797c79.png

This URL can be used to view or download the generated image.

Conceptual Usage Example (Python)

Here's how a developer might implement the Generate Image with NOVA action using Python. This snippet demonstrates how to structure the input JSON payload and make a request to a hypothetical Cognitive Actions execution endpoint.

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 = "a3a53a89-6247-49a7-93c3-90388558e09e" # Action ID for Generate Image with NOVA

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "a shiba inu wearing a beret and black turtleneck.",
    "guidanceScale": 5,
    "negativePrompt": "low quality, deformed, distorted, disfigured, fused fingers, bad anatomy, weird hand",
    "numberOfDiffusionSteps": 25,
    "numberOfInferenceSteps": 64
}

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_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is structured based on the input schema we discussed. The endpoint URL and request structure are hypothetical and should be adjusted to match your specific implementation.

Conclusion

The Generate Image with NOVA action presents a powerful tool for developers looking to integrate image generation capabilities into their applications. With customizable prompts and control over the generation process, you can create unique visuals tailored to your needs. Explore the possibilities and enhance your applications with stunning images generated using the chenxwh/nova-t2i Cognitive Actions!

← Back to All Articles