Generate Stunning Images with Cognitive Actions from jhorovitz/inversions

24 Apr 2025
Generate Stunning Images with Cognitive Actions from jhorovitz/inversions

In the world of artificial intelligence and machine learning, image generation has become a fascinating and highly sought-after application. The jhorovitz/inversions API provides developers with powerful Cognitive Actions that enable image generation using RF inversion techniques. These pre-built actions help streamline the process of creating images from textual prompts and existing images, offering various controls for output quality and characteristics. This guide will delve into how you can leverage the Generate Image with RF Inversion action to harness the power of this API.

Prerequisites

Before you start using the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform. This is essential for authenticating requests.
  • Basic understanding of JSON and Python for constructing requests and handling responses.

Authentication typically involves passing your API key in the headers of your requests.

Cognitive Actions Overview

Generate Image with RF Inversion

This action generates images using RF inversion sampling from a given text prompt and an input image URI. It offers various controls over aspects like guidance strength, output format, image quality, and more.

Input

The input schema for this action requires a JSON object, which includes the following fields:

  • prompt (required): The text prompt for generating the image.
  • image (optional): URI of the input image for image-to-image transformation.
  • guidance (optional): Determines the guidance strength for image generation, ranging from 0 to 10.
  • outputCount (optional): Specifies the number of output images to generate (1-4).
  • imageOutputFormat (optional): The file format for the output images (e.g., WEBP, JPG, PNG).
  • outputAspectRatio (optional): Aspect ratio for the generated image in width:height format.

Here’s an example of a typical input JSON payload:

{
  "eta": 1,
  "image": "https://replicate.delivery/pbxt/LxgKJVnzPNl1XhlGCcK75xtHnQ1RUs9emmR4ULSv6RFRtKTD/resized_image.jpg",
  "prompt": "A man wearing glasses",
  "fastMode": false,
  "guidance": 3,
  "finalStep": 6,
  "initialStep": 2,
  "outputCount": 1,
  "imgToImgMode": "rf_inversion",
  "approxMegapixels": "1",
  "imageOutputFormat": "png",
  "outputAspectRatio": "1:1",
  "imageOutputQuality": 100,
  "inferenceStepCount": 28,
  "imagePromptStrength": 1
}

Output

Upon successful execution, the action returns an array containing the URLs of the generated images. Here’s an example of the typical output:

[
  "https://assets.cognitiveactions.com/invocations/aa1779b5-25fb-4fc7-bde2-820f69e23a5d/700e32fb-cfc7-49cb-9825-07620c481a66.png"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to call the Cognitive Actions endpoint for this 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 = "2017cdf0-d5a9-4256-8920-2a2c24e9ff36"  # Action ID for Generate Image with RF Inversion

# Construct the input payload based on the action's requirements
payload = {
  "eta": 1,
  "image": "https://replicate.delivery/pbxt/LxgKJVnzPNl1XhlGCcK75xtHnQ1RUs9emmR4ULSv6RFRtKTD/resized_image.jpg",
  "prompt": "A man wearing glasses",
  "fastMode": false,
  "guidance": 3,
  "finalStep": 6,
  "initialStep": 2,
  "outputCount": 1,
  "imgToImgMode": "rf_inversion",
  "approxMegapixels": "1",
  "imageOutputFormat": "png",
  "outputAspectRatio": "1:1",
  "imageOutputQuality": 100,
  "inferenceStepCount": 28,
  "imagePromptStrength": 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 code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable contains the structured JSON input required for the action. The response will contain the URLs of the generated images, which can be printed or used as needed.

Conclusion

The jhorovitz/inversions Cognitive Action for generating images with RF inversion provides powerful capabilities for developers looking to integrate advanced image generation features into their applications. By utilizing the specified input parameters, you can control various aspects of the image generation process, ensuring that the outputs meet your specific needs. Explore potential use cases such as generating artwork, enhancing product images, or creating unique visual content for your projects. Happy coding!

← Back to All Articles