Enhance Image Generation with Cognitive Actions from jhorovitz/redux-slider-schnell

24 Apr 2025
Enhance Image Generation with Cognitive Actions from jhorovitz/redux-slider-schnell

Integrating image processing capabilities into your applications can significantly enhance user experience and engagement. The jhorovitz/redux-slider-schnell Cognitive Actions provide powerful pre-built actions for manipulating image generation. Specifically, these actions allow developers to fine-tune various parameters, such as prompt strength, to achieve desired artistic outcomes while maintaining consistency in results. In this article, we will explore how to utilize the "Tune Image Prompt Strength" action effectively.

Prerequisites

Before diving into the integration, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with making HTTP requests and handling JSON data in your programming environment.

Typically, authentication is handled by passing the API key in the headers of your requests.

Cognitive Actions Overview

Tune Image Prompt Strength

Purpose:
The "Tune Image Prompt Strength" action allows you to adjust the strength of the prompt to modify the editing style and content in image generation. This flexibility enables you to create images that closely align with your intended vision.

Category:
Image Processing

Input

The input for this action is structured as follows:

{
  "seed": 42,
  "redux": "https://replicate.delivery/pbxt/MHocNcBT9rCyEg704LnolXXFDwf10UzowHqvJ2bYJ83CdCEa/car.webp",
  "width": 1024,
  "height": 1024,
  "prompt": "A cartoon drawing of a car.",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 80,
  "reduxStrength": 0.03,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 4
}

Field Descriptions:

  • seed (integer): A random seed to ensure reproducible generation.
  • redux (string): URL of the redux image used during processing.
  • width (integer): Width of the output image in pixels (default is 1024).
  • height (integer): Height of the output image in pixels (default is 1024).
  • prompt (string): Descriptive text for image generation.
  • outputFormat (string): File format of the output images (options: 'webp', 'jpg', 'png', default is 'webp').
  • guidanceScale (number): Scale used during the diffusion process (0 to 10, default is 3.5).
  • outputQuality (integer): Quality of the output images, from 0 to 100 (default is 80, not relevant for .png).
  • reduxStrength (number): Strength of the Redux image (values between 0.01 and 0.1 are recommended).
  • numberOfOutputs (integer): Number of images to generate (default is 1, can be from 1 to 4).
  • numberOfInferenceSteps (integer): Steps during inference (1 to 50, default is 4).

Output

The output of this action is an array of URLs pointing to the generated images. Here’s an example of what you might receive:

[
  "https://assets.cognitiveactions.com/invocations/c13ff9d7-11c4-4a92-8f20-77bc9bf77e2c/360cb125-6b9a-44e0-b03f-7472c9108deb.webp"
]

This output contains the URLs of the generated images based on the input parameters provided.

Conceptual Usage Example (Python)

Here’s how you might structure your request to invoke 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 = "a048bf2b-de68-4b23-ba19-2c9642ea7388"  # Action ID for Tune Image Prompt Strength

# Construct the input payload based on the action's requirements
payload = {
    "seed": 42,
    "redux": "https://replicate.delivery/pbxt/MHocNcBT9rCyEg704LnolXXFDwf10UzowHqvJ2bYJ83CdCEa/car.webp",
    "width": 1024,
    "height": 1024,
    "prompt": "A cartoon drawing of a car.",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 80,
    "reduxStrength": 0.03,
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 4
}

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:

  • We replace the API key and the action ID with your specific details.
  • The input payload is constructed based on the required fields for the action.
  • The response is processed to extract the URLs of the generated images.

Conclusion

The "Tune Image Prompt Strength" action from the jhorovitz/redux-slider-schnell Cognitive Actions is a powerful tool for developers looking to enhance their image generation capabilities. By adjusting parameters such as reduxStrength and guidanceScale, you can create diverse and visually appealing outputs tailored to your needs. Start integrating these Cognitive Actions into your applications today and explore the creative possibilities they unlock!

← Back to All Articles