Generate Stunning Images with sjones8959/sjfx Cognitive Actions

24 Apr 2025
Generate Stunning Images with sjones8959/sjfx Cognitive Actions

In the world of digital creativity, generating high-quality images can be a game-changer for developers and artists alike. The sjones8959/sjfx API offers a powerful Cognitive Action called Generate Image Inpainting that enables users to create exquisite images by utilizing advanced image generation techniques. This action allows you to customize the output through various parameters, making it ideal for diverse applications ranging from content creation to artistic projects.

Prerequisites

Before you embark on using the Generate Image Inpainting action, ensure you have the following:

  • An API key for the sjones8959/sjfx platform to authenticate your requests.
  • Basic understanding of JSON structure, as the input and output will be in this format.

To authenticate your requests, you will generally include your API key in the headers of your HTTP requests, typically as follows:

Authorization: Bearer YOUR_API_KEY

Cognitive Actions Overview

Generate Image Inpainting

The Generate Image Inpainting action is designed to produce high-quality images using either inpainting or image-to-image modes. This action allows you to customize the image generation process by providing a variety of parameters such as masks, seeds, dimensions, and model types, utilizing optimized models for both detail and speed.

Input

The input schema for this action is a JSON object with the following required and optional fields:

  • Required Fields:
    • prompt: A descriptive string that outlines what you want to generate.
  • Optional Fields:
    • mask: (URI) An image mask for inpainting mode.
    • seed: (integer) A random seed for reproducibility.
    • image: (URI) Input image for transformations.
    • width: (integer) Width of the generated image (when aspect ratio is custom).
    • height: (integer) Height of the generated image (when aspect ratio is custom).
    • accelerate: (boolean) Enables faster predictions.
    • aspectRatio: (string) Defines the aspect ratio for the generated image.
    • imageFormat: (string) Specifies the format of the output images.
    • Additional various parameters for controlling quality, intensity, and model use.

Here’s an example of a JSON payload you might send when calling this action:

{
  "image": "https://replicate.delivery/pbxt/MQ3cUzTXRO6jFvIC7qNy8kZQ6wIxhExU3ehOVsgP4lHDqRFf/a-high-quality-professional-photo-of-a-t_rlHy2gArQembiAVtFRC0XQ_nwTDmoLKR9-ORkchcEO3Mg.png",
  "width": 1346,
  "prompt": "Birds eye view + A high-quality professional photo of a striking stunning pretty gorgeous beautiful African American woman standing confidently outside the Citi Headquarters building in New York...",
  "accelerate": false,
  "aspectRatio": "1:1",
  "imageFormat": "webp",
  "outputCount": 4,
  "denoiseSteps": 45,
  "imageQuality": 84,
  "guidanceScale": 9.01,
  "loraIntensity": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageResolution": "1",
  "additionalLoraScale": 1
}

Output

The output of the action is a list of URLs pointing to the generated images. For example:

[
  "https://assets.cognitiveactions.com/invocations/a5434860-1dd8-434a-bb6d-8527ec22f80d/c3dd54a6-b7c3-4729-b4b2-353de6ed24b8.webp",
  "https://assets.cognitiveactions.com/invocations/a5434860-1dd8-434a-bb6d-8527ec22f80d/fde951d4-ce04-41fd-9964-723bcec26552.webp",
  "https://assets.cognitiveactions.com/invocations/a5434860-1dd8-434a-bb6d-8527ec22f80d/d4d2e62b-91fa-4fe1-b817-6d65fed13133.webp",
  "https://assets.cognitiveactions.com/invocations/a5434860-1dd8-434a-bb6d-8527ec22f80d/fae4204f-6eab-4fd9-b219-66230a1cbcf9.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet that demonstrates how you might call the Generate Image Inpainting 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 = "9c1181d3-6c35-45c8-a451-1701375b8614"  # Action ID for Generate Image Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/MQ3cUzTXRO6jFvIC7qNy8kZQ6wIxhExU3ehOVsgP4lHDqRFf/a-high-quality-professional-photo-of-a-t_rlHy2gArQembiAVtFRC0XQ_nwTDmoLKR9-ORkchcEO3Mg.png",
    "width": 1346,
    "prompt": "Birds eye view + A high-quality professional photo of a striking stunning pretty gorgeous beautiful African American woman standing confidently outside the Citi Headquarters building in New York...",
    "accelerate": False,
    "aspectRatio": "1:1",
    "imageFormat": "webp",
    "outputCount": 4,
    "denoiseSteps": 45,
    "imageQuality": 84,
    "guidanceScale": 9.01,
    "loraIntensity": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageResolution": "1",
    "additionalLoraScale": 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 snippet, you’ll replace the API key and endpoint with your own. The action_id corresponds to the Generate Image Inpainting action. The payload is structured according to the required and optional parameters, ensuring that the request adheres to the expectations of the API.

Conclusion

The Generate Image Inpainting action from the sjones8959/sjfx API provides developers with a robust tool for high-quality image generation. By leveraging the various customizable parameters, you can create stunning visuals tailored to your specific needs. Whether you're working on creative projects, marketing materials, or artistic endeavors, this action opens up a world of possibilities. Start integrating it into your applications today and explore the creative potential at your fingertips!

← Back to All Articles