Generate Stunning Images from Text Prompts Using cjwbw/karlo Cognitive Actions

21 Apr 2025
Generate Stunning Images from Text Prompts Using cjwbw/karlo Cognitive Actions

In today's digital landscape, creating high-quality visual content can be a daunting task, especially when it comes to generating images from textual descriptions. The cjwbw/karlo API provides a powerful solution through its Cognitive Actions, specifically designed for image generation. These pre-built actions allow developers to leverage advanced models like Karlo to create stunning images based on detailed text prompts, enhancing their applications with minimal effort. In this post, we'll explore the capabilities of the Karlo action and how you can integrate it into your projects.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Basic knowledge of HTTP requests and JSON.
  • A suitable development environment set up for making API calls.

For authentication, you will typically pass the API key in the headers of your requests, allowing secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Text-Conditional Images with Karlo

The Generate Text-Conditional Images with Karlo action allows users to generate high-resolution images based on textual descriptions. Utilizing the advanced capabilities of the Karlo model, this action is equipped with improved super-resolution techniques derived from OpenAI's unCLIP architecture, enabling creators to produce visually appealing images that closely match their input prompts.

Input

The input for this action is structured as follows:

  • prompt (string): The textual description that guides the image generation.
    • Example: "a high-resolution photograph of a big red frog on a green leaf"
  • seed (integer, optional): Specifies the random seed for image generation. Leaving it blank will randomize the seed.
  • priorGuidanceScale (number): Controls adherence to the text prompt during the prior stage.
    • Default: 4
  • decoderGuidanceScale (number): Controls adherence to the text prompt during the decoder stage.
    • Default: 8
  • numberOfImagesPerPrompt (integer): The number of images to generate for each input prompt.
    • Options: 1 or 4
  • priorNumberOfInferenceSteps (integer): Number of denoising steps during the prior stage.
    • Default: 25
  • decoderNumberOfInferenceSteps (integer): Number of denoising steps during the decoder stage.
    • Default: 25
  • superResolutionNumberOfInferenceSteps (integer): Number of denoising steps during the super-resolution stage.
    • Default: 7

Here is a practical example of the JSON payload needed to invoke this action:

{
  "prompt": "a high-resolution photograph of a big red frog on a green leaf",
  "priorGuidanceScale": 4,
  "decoderGuidanceScale": 8,
  "numberOfImagesPerPrompt": 1,
  "priorNumberOfInferenceSteps": 25,
  "decoderNumberOfInferenceSteps": 25,
  "superResolutionNumberOfInferenceSteps": 7
}

Output

Upon successful execution, the action returns a list of URLs pointing to the generated images. For example:

[
  "https://assets.cognitiveactions.com/invocations/6f4196bc-f756-4512-b97c-87571bfa8ed0/036aba99-8dbd-411a-8d7d-4508c8b33914.png"
]

This URL can be used to display the generated image in your application.

Conceptual Usage Example (Python)

Here’s how you might call the Generate Text-Conditional Images with Karlo 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 = "f8d00127-40b3-449e-8232-a25b9f91712f"  # Action ID for Generate Text-Conditional Images with Karlo

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "a high-resolution photograph of a big red frog on a green leaf",
    "priorGuidanceScale": 4,
    "decoderGuidanceScale": 8,
    "numberOfImagesPerPrompt": 1,
    "priorNumberOfInferenceSteps": 25,
    "decoderNumberOfInferenceSteps": 25,
    "superResolutionNumberOfInferenceSteps": 7
}

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, replace the placeholder for the API key with your actual key. The action ID and input payload are structured according to the specifications provided, allowing you to generate an image based on a given text prompt.

Conclusion

The cjwbw/karlo Cognitive Actions empower developers to create high-quality images from textual descriptions with ease. By integrating these actions into your applications, you can enhance user experience and expand the creative possibilities of your projects. Start exploring the potential of text-conditional image generation today, and consider additional use cases where visual content creation can elevate your application. Happy coding!

← Back to All Articles