Enhance Your Applications with sagolab/faceai: A Guide to Image Generation Actions

23 Apr 2025
Enhance Your Applications with sagolab/faceai: A Guide to Image Generation Actions

In today's digital landscape, the ability to generate and manipulate images dynamically can significantly enhance user experiences. The sagolab/faceai API provides a powerful set of Cognitive Actions to facilitate advanced image generation and inpainting capabilities. These pre-built actions allow developers to create stunning visuals tailored to specific prompts and requirements, saving time and effort while delivering high-quality outputs.

Prerequisites

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

  • API Key: You will need to obtain an API key from the Cognitive Actions platform for authentication.
  • Setup: Familiarize yourself with the API documentation and endpoint structure.

Authentication typically involves passing the API key in the request headers to authorize your API calls.

Cognitive Actions Overview

Generate and Inpaint Image with Refinement

This action generates and inpaints images based on a specified prompt and mask, providing options for image customization through various parameters. It supports multiple refiners for quality enhancement and allows control over scheduling algorithms and watermark application.

Input

The input for this action requires a JSON object that can include the following fields:

  • mask (string, optional): URI of the input mask for inpainting mode.
  • seed (integer, optional): Random seed for generation.
  • image (string, optional): URI of the input image for img2img or inpaint mode.
  • width (integer, default: 1024): Width of the output image.
  • height (integer, default: 1024): Height of the output image.
  • prompt (string): Text prompt guiding the image generation.
  • refine (string, default: "no_refiner"): Style of refinement.
  • scheduler (string, default: "K_EULER"): Scheduling algorithm for generation.
  • customWeights (string, optional): Custom LoRA weights.
  • loraIntensity (number, default: 0.6): Intensity of LoRA.
  • applyWatermark (boolean, default: true): Apply a watermark to the image.
  • numberOfOutputs (integer, default: 1): Number of images to generate (1-4).
  • refinementSteps (integer, optional): Steps for base image refinement.
  • guidanceIntensity (number, default: 7.5): Intensity of classifier-free guidance.
  • highNoiseFraction (number, default: 0.8): Fraction of noise for expert refiner.
  • inferenceStepsCount (integer, default: 50): Number of denoising steps.
  • inputPromptStrength (number, default: 0.8): Strength of the input prompt.
  • negativeInputPrompt (string, optional): A prompt to guide generation away from certain elements.
  • disableImageSafetyCheck (boolean, default: false): Disable safety checks for generated images.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "portrait photo of TOK at Tokyo with flower",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "loraIntensity": 0.6,
  "applyWatermark": true,
  "numberOfOutputs": 1,
  "guidanceIntensity": 7.5,
  "highNoiseFraction": 0.8,
  "inferenceStepsCount": 50,
  "inputPromptStrength": 0.8
}

Output

Upon successful execution, the action returns an array of generated image URLs, with the first element being the primary output image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/5f6c4a35-9e9c-499c-8588-6bad78027159/8841d97a-58d8-4ce4-8a77-d0c820acafaa.png"
]

Conceptual Usage Example (Python)

Here's a conceptual example of how you might call this 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 = "f8799e66-584a-4fd1-afe7-a63904c0717d"  # Action ID for Generate and Inpaint Image with Refinement

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "portrait photo of TOK at Tokyo with flower",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "loraIntensity": 0.6,
    "applyWatermark": True,
    "numberOfOutputs": 1,
    "guidanceIntensity": 7.5,
    "highNoiseFraction": 0.8,
    "inferenceStepsCount": 50,
    "inputPromptStrength": 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 example, replace the API key and endpoint with your actual credentials. The payload is constructed based on the required parameters for the action, allowing for dynamic image generation based on the provided prompt.

Conclusion

The sagolab/faceai API offers robust Cognitive Actions for developers looking to integrate advanced image generation capabilities into their applications. By leveraging the Generate and Inpaint Image with Refinement action, you can create stunning visuals tailored to your users' needs. Explore the possibilities of image generation and enhance your applications with these powerful tools today!

← Back to All Articles