Generate Stunning Images with the omarprama/xot-batch-8 Cognitive Actions

20 Apr 2025
Generate Stunning Images with the omarprama/xot-batch-8 Cognitive Actions

In today's world, where visual content is crucial for engagement, the ability to generate images programmatically can be a game-changer for developers. The omarprama/xot-batch-8 specification provides a powerful set of Cognitive Actions that make image generation easy and customizable. With the ability to specify parameters like aspect ratio, dimensions, and even inpainting capabilities, developers can create tailored visuals that meet their specific needs. Let’s dive into how to leverage these pre-built actions effectively.

Prerequisites

Before you start using the Cognitive Actions, ensure you have an API key for the Cognitive Actions platform. Typically, you would authenticate your requests by including this API key in the headers of your HTTP calls.

Cognitive Actions Overview

Generate Image with Customizable Settings

The Generate Image with Customizable Settings action allows you to create images based on various customizable parameters. Whether you need to specify an aspect ratio, dimensions, or provide a prompt, this action covers it all. It also supports advanced features like inpainting and LoRA weight customization.

Input

The input for this action is structured as follows:

  • prompt: (required) A textual prompt guiding the image generation.
  • mask: (optional) An image mask for inpainting mode.
  • seed: (optional) A random seed for reproducibility.
  • image: (optional) An input image for image-to-image or inpainting mode.
  • model: (optional) Model type for inference (either "dev" or "schnell").
  • width: (optional) Width of the generated image (256 to 1440).
  • height: (optional) Height of the generated image (256 to 1440).
  • loraScale: (optional) Strength of the main LoRA application.
  • speedMode: (optional) Enable fast predictions (default: false).
  • megapixels: (optional) Estimated megapixels of the generated image.
  • aspectRatio: (optional) Aspect ratio for the image, with options including "1:1", "16:9", and others.
  • outputCount: (optional) Number of images to generate (1 to 4).
  • outputFormat: (optional) Desired output file format (e.g., "webp", "jpg", "png").
  • guidanceScale: (optional) Scale used in the diffusion process.
  • outputQuality: (optional) Quality level for output images (0 to 100).
  • inferenceSteps: (optional) Denoising steps for image detail.
  • promptStrength: (optional) Strength of prompt application in img2img mode.
  • loraWeights: (optional) Load additional LoRA weights.
  • modelWeights: (optional) Load model weights from specific sources.
  • disableSafetyChecker: (optional) Option to disable the safety checker.

Example Input:

{
  "model": "dev",
  "prompt": "front view, of a tall white man with ginger hair wearing OXT and grey shorts and flipflops, professional photo",
  "loraScale": 1,
  "aspectRatio": "1:1",
  "outputCount": 1,
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "inferenceSteps": 28,
  "promptStrength": 0.8,
  "loraWeightsScale": 1
}

Output

The expected output from this action will typically be a URL pointing to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/577c77a4-5c8b-4342-902b-25cb3584ccb3/69a29fb2-b056-4550-809b-dc7e06cc6bed.webp"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet demonstrating how to invoke the Generate Image with Customizable Settings action:

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 = "be7961fc-7d47-4949-9ce0-48824a28bfd5"  # Action ID for Generate Image with Customizable Settings

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "front view, of a tall white man with ginger hair wearing OXT and grey shorts and flipflops, professional photo",
    "loraScale": 1,
    "aspectRatio": "1:1",
    "outputCount": 1,
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "inferenceSteps": 28,
    "promptStrength": 0.8,
    "loraWeightsScale": 1
}

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, the code constructs a JSON payload based on the required parameters for the action. It includes the action ID and sends a POST request to the hypothetical Cognitive Actions execution endpoint.

Conclusion

The omarprama/xot-batch-8 Cognitive Actions offer developers a robust solution for image generation with customizable settings. With capabilities like inpainting, aspect ratio adjustments, and various output formats, these actions can enhance any application requiring dynamic visual content. Explore the possibilities of integrating these actions into your projects, and elevate your application's visual appeal!

← Back to All Articles