Generate Stunning Images with the shoshosho77/sina-test2 Cognitive Action

22 Apr 2025
Generate Stunning Images with the shoshosho77/sina-test2 Cognitive Action

In the realm of artificial intelligence, image generation has emerged as a powerful tool that allows developers to create unique visuals based on textual prompts. The shoshosho77/sina-test2 API provides a seamless way to integrate image generation capabilities into your applications through its pre-built Cognitive Actions. This article will guide you on how to utilize the "Perform Image Generation" action, which offers a robust set of options for customizing image outputs, including inpainting, aspect ratios, and more.

Prerequisites

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

  • An API key for the Cognitive Actions platform. This key will be used for authentication to access the services.
  • Basic knowledge of how to structure JSON payloads, as the API expects data in JSON format.

Authentication generally involves passing the API key in the request headers to verify your identity as a user.

Cognitive Actions Overview

Perform Image Generation

The Perform Image Generation action is designed to generate images based on user-defined prompts. It supports various customizable parameters such as image inpainting, aspect ratios, and selectable models for optimized performance.

Input

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

  • prompt (required): Text prompt used to generate the image.
  • mask (optional): URI of the image mask for inpainting.
  • seed (optional): Random seed value for reproducibility.
  • image (optional): URI of the input image for image-to-image conversions.
  • model (optional): The inference model to use (default is "dev").
  • width (optional): Specifies the width for custom aspect ratios.
  • goFast (optional): Enables fast predictions.
  • height (optional): Specifies the height for custom aspect ratios.
  • extraLora (optional): Loads additional LoRA weights.
  • loraScale (optional): Adjusts the intensity of LoRA application.
  • megapixels (optional): Specifies the number of megapixels for the generated image.
  • outputFormat (optional): Specifies the output format (default is "webp").
  • guidanceScale (optional): Sets the guidance scale for the diffusion process.
  • outputQuality (optional): Specifies the quality of output images.
  • extraLoraScale (optional): Controls the strength of extra LoRA application.
  • promptStrength (optional): Determines the prompt strength for image-to-image conversion.
  • numberOfOutputs (optional): Specifies how many output images to generate (max 4).
  • imageAspectRatio (optional): Sets the aspect ratio for the generated image.
  • turnOffSafetyChecker (optional): Option to disable the safety checker.
  • numberOfInferenceSteps (optional): Number of denoising steps for image generation.

Example Input:

{
  "model": "dev",
  "goFast": false,
  "prompt": "aesthetic black and white photo of SINA sitting on a stool looking slightly down",
  "loraScale": 1,
  "megapixels": "1",
  "outputFormat": "webp",
  "guidanceScale": 3,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "numberOfOutputs": 2,
  "imageAspectRatio": "4:5",
  "numberOfInferenceSteps": 28
}

Output

The output from this action is a list of URLs pointing to the generated images based on the provided prompt and parameters.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/3c82933d-eb22-4a02-987f-57d4abe929b0/9016d4bb-8c76-407a-be16-ecd98fb8704c.webp",
  "https://assets.cognitiveactions.com/invocations/3c82933d-eb22-4a02-987f-57d4abe929b0/559936ee-2998-4b9a-9c48-0536ba3dd8fd.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to call the "Perform Image Generation" action using 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 = "b7e213f9-21d7-4d9e-9977-c0e38173fb39"  # Action ID for Perform Image Generation

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "aesthetic black and white photo of SINA sitting on a stool looking slightly down",
    "loraScale": 1,
    "megapixels": "1",
    "outputFormat": "webp",
    "guidanceScale": 3,
    "outputQuality": 80,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "numberOfOutputs": 2,
    "imageAspectRatio": "4:5",
    "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 code snippet, you'll need to replace the placeholder for the API key and ensure that the action ID corresponds to the "Perform Image Generation" action. The input payload is structured according to the specifications, allowing for a comprehensive image generation request.

Conclusion

The shoshosho77/sina-test2 Cognitive Action provides developers with a powerful tool to generate images effortlessly based on textual descriptions. By leveraging customizable parameters, you can create unique and visually appealing outputs suited for various applications. Next steps could include experimenting with different prompts, adjusting model parameters, or integrating this functionality into a broader application. Happy coding!

← Back to All Articles