Create Stunning Images with Diyo's Cognitive Actions for Developers

22 Apr 2025
Create Stunning Images with Diyo's Cognitive Actions for Developers

In the world of artificial intelligence, the ability to generate images based on textual descriptions has opened up numerous opportunities for developers. The diyomatalo/diyo API offers powerful Cognitive Actions that allow you to create images using inpainting and image-to-image modes, all customizable to your needs. This article will guide you through the specifics of these actions, showcasing their potential and how to effectively integrate them into your applications.

Prerequisites

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

  • API Key: You will need an API key to authenticate your requests. This key should be included in the headers of your API calls.
  • Basic Knowledge of JSON: Familiarity with JSON structure will help you understand the input and output formats required for the actions.

Authentication Concept

Authentication typically requires you to pass the API key in the headers of your requests, allowing secure access to the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with Inpainting and Custom Settings

Description: This action allows you to generate images using inpainting and image-to-image modes, with customizable settings such as aspect ratio, dimensions, quality, and additional LoRA weights. The operation supports varying model types for optimal inference speed and quality.

Category: Image Generation

Input

The input to this action requires the following fields:

  • prompt (required): A textual description guiding the image generation (e.g., "close up shot of TRDIYO a black man on his way").
  • mask (optional): URI of the image mask for inpainting mode.
  • image (optional): URI of the input image for transformations.
  • model (default: "dev"): Selects the model for inference (options: "dev", "schnell").
  • width (optional): Specifies the width for the generated image.
  • height (optional): Specifies the height for the generated image.
  • outputCount (default: 1): Number of images to generate (1-4).
  • outputFormat (default: "webp"): Format for the output images (options: "webp", "jpg", "png").
  • guidanceScale (default: 3): Adjusts the realism of the image.
  • outputQuality (default: 80): Quality of the output images (0-100).
  • inferenceSteps (default: 28): Defines the number of denoising steps.

Example Input:

{
  "model": "dev",
  "prompt": "close up shot of TRDIYO a black man on his way",
  "loraScale": 1,
  "aspectRatio": "1:1",
  "outputCount": 3,
  "outputFormat": "png",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceSteps": 20,
  "promptStrength": 0.8
}

Output

The output of this action will typically include URLs to the generated images. For example:

[
  "https://assets.cognitiveactions.com/invocations/812a073f-cf4c-46b3-a1f9-fbf43aa4476c/b22cefb0-936d-4a6b-8645-7893d7b4422a.png",
  "https://assets.cognitiveactions.com/invocations/812a073f-cf4c-46b3-a1f9-fbf43aa4476c/f4f330b4-dd33-47df-8ea6-f40b65c2f128.png",
  "https://assets.cognitiveactions.com/invocations/812a073f-cf4c-46b3-a1f9-fbf43aa4476c/4a0e414c-f98e-48fe-a1fa-1d423d595fd9.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet to demonstrate how you might call the Generate Image with Inpainting and Custom 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 = "20bb2de8-4ee9-42ee-a987-44d1d942707a"  # Action ID for Generate Image with Inpainting and Custom Settings

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "close up shot of TRDIYO a black man on his way",
    "loraScale": 1,
    "aspectRatio": "1:1",
    "outputCount": 3,
    "outputFormat": "png",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceSteps": 20,
    "promptStrength": 0.8
}

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 need to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is structured to align with the input schema of the action, ensuring proper data is sent to the server.

Conclusion

The diyomatalo/diyo Cognitive Actions provide a robust and flexible way to generate images tailored to your specifications. By leveraging these actions, developers can enhance their applications with powerful image generation capabilities. As you explore further, consider integrating other features or experimenting with different parameters to unlock even more creative possibilities. Happy coding!

← Back to All Articles