Generate Stunning Images with the anastasypetrova/nastia Cognitive Actions

23 Apr 2025
Generate Stunning Images with the anastasypetrova/nastia Cognitive Actions

In today's digital landscape, creating high-quality visuals is paramount. The anastasypetrova/nastia API offers powerful Cognitive Actions that allow developers to generate images through advanced techniques like inpainting and image-to-image transformations. By leveraging these pre-built actions, you can efficiently create captivating visuals tailored to your application's needs.

Prerequisites

Before you get started with the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Familiarity with JSON format for input and output data structures.
  • Basic knowledge of making HTTP requests in your preferred programming language.

Authentication typically involves passing your API key in the request headers, enabling you to access the actions securely.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create images using either image-to-image transformations or inpainting modes. It features customizable settings such as aspect ratio, resolution, and model selection, making it ideal for generating high-quality visuals or optimizing for speed.

Input

The input for this action requires a JSON object that includes a prompt, which is essential for generating the image. Here’s a breakdown of the input schema:

  • Required:
    • prompt: A string detailing the scene or object to be generated.
  • Optional:
    • mask: URI of the mask image for inpainting.
    • seed: Integer for reproducibility.
    • image: URI of the input image.
    • model: Specifies which model to use (default is "dev").
    • width and height: Dimensions of the generated image.
    • goFast: Boolean to enable faster generation.
    • megapixels: Approximate output image size.
    • aspectRatio: Desired aspect ratio for the image.
    • (And several others...)

Example Input:

{
  "model": "dev",
  "goFast": false,
  "prompt": "NASTIA is sitting at an elegant Parisian café, sipping a cappuccino...",
  "megapixels": "1",
  "aspectRatio": "3:4",
  "mainLoraScale": 1,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "additionalLoraScale": 1,
  "diffusionGuidanceScale": 3,
  "numberOfInferenceSteps": 28
}

Output

The action typically returns a list containing the URLs of the generated images. Here’s an example of the output:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e67c6a23-b27c-4fa1-9907-e5c5d7690e31/4e4a9fc0-685c-4b32-8075-309031a497b5.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image with Inpainting 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 = "e9c914ba-2a3c-42f3-ac8e-1dff72c5b139"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "NASTIA is sitting at an elegant Parisian café, sipping a cappuccino...",
    "megapixels": "1",
    "aspectRatio": "3:4",
    "mainLoraScale": 1,
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "additionalLoraScale": 1,
    "diffusionGuidanceScale": 3,
    "numberOfInferenceSteps": 28
}

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 example, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload structure aligns with the input schema outlined above, ensuring that you provide all necessary parameters for the image generation.

Conclusion

The anastasypetrova/nastia Cognitive Action for generating images with inpainting offers developers a robust tool for creating stunning visuals efficiently. With customizable settings and the ability to leverage different models, you can enhance your applications' visual appeal effortlessly. Explore this action further and consider integrating it into projects requiring dynamic and engaging imagery!

← Back to All Articles