Generate Stunning Images with Cognitive Actions from the tina94b/nikki Spec

23 Apr 2025
Generate Stunning Images with Cognitive Actions from the tina94b/nikki Spec

In the world of AI-driven creativity, the tina94b/nikki specification offers powerful Cognitive Actions that enable developers to generate stunning images through inpainting techniques. These pre-built actions streamline the image generation process, allowing for custom aspect ratios, multiple outputs, and various output formats, all while optimizing for speed. Let’s dive into how you can leverage this functionality in your applications.

Prerequisites

Before you can start using the Cognitive Actions, ensure you have an API key for the Cognitive Actions platform. Authentication typically involves passing this key in the headers of your requests.

Here’s how you might structure the headers in a request:

headers = {
    "Authorization": f"Bearer {YOUR_API_KEY}",
    "Content-Type": "application/json"
}

Cognitive Actions Overview

Generate Image Using Inpainting

Purpose

The Generate Image Using Inpainting action allows you to create images using inpainting techniques. This method supports various customizations, including aspect ratios and prompt influences, making it ideal for both image-to-image transformations and unique artistic creations.

Input

The input for this action requires a JSON object containing the following fields:

  • prompt (required): This is the main textual description of what the image should depict.
  • mask (optional): URI of an image mask used for inpainting; if provided, other dimension inputs are ignored.
  • seed (optional): An integer seed for deterministic image generation, ensuring consistent results across different runs.
  • image (optional): URI of an input image for processing or inpainting; if provided, other dimension inputs are ignored.
  • model (optional): Choose between "dev" (28 inference steps) or "schnell" (4 steps).
  • width and height (optional): Specify dimensions when the aspect ratio is set to "custom".
  • goFast (optional): Enable faster predictions using optimized models.
  • aspectRatio (optional): Select the aspect ratio for the generated image.
  • Other optional fields include numOutputs, outputFormat, guidanceScale, and various scaling parameters.

Here’s a practical example of the required JSON payload:

{
  "model": "dev",
  "goFast": false,
  "prompt": "This is a photograph of a middle-aged man smiling and winking with one eye, he has a grey beard and mustache, wearing a grey suit and white shirt, seated at a wooden desk.",
  "loraScale": 1,
  "megapixels": "1",
  "numOutputs": 2,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "numInferenceSteps": 28
}

Output

The output from this action consists of URLs pointing to the generated images. Here's an example of what you might receive:

[
  "https://assets.cognitiveactions.com/invocations/example1.webp",
  "https://assets.cognitiveactions.com/invocations/example2.webp"
]

Conceptual Usage Example (Python)

To call the Generate Image Using Inpainting action using Python, you could structure your code as follows:

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 = "d490c7c4-2df6-4b3a-baa8-b15f6547e4aa"  # Action ID for Generate Image Using Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "This is a photograph of a middle-aged man smiling and winking with one eye, he has a grey beard and mustache, wearing a grey suit and white shirt, seated at a wooden desk.",
    "loraScale": 1,
    "megapixels": "1",
    "numOutputs": 2,
    "aspectRatio": "1:1",
    "outputFormat": "webp",
    "guidanceScale": 3,
    "outputQuality": 80,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "numInferenceSteps": 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 code snippet, make sure to replace the endpoint and action ID appropriately. The payload is constructed based on the input schema provided for the action.

Conclusion

The tina94b/nikki Cognitive Actions provide an impressive suite of capabilities for generating images through inpainting techniques. By leveraging these actions, developers can enhance their applications with rich visual content, tailored to specific requirements. Whether you’re creating art, enhancing user experiences, or developing unique visual assets, these actions open up a world of possibilities. Start experimenting with them today!

← Back to All Articles