Generate Stunning Images with the akisakurai/stable-karlo Cognitive Actions

21 Apr 2025
Generate Stunning Images with the akisakurai/stable-karlo Cognitive Actions

In today's world of artificial intelligence, generating images from textual descriptions is not only a fascinating concept but also a powerful tool for developers. The akisakurai/stable-karlo Cognitive Actions provide a seamless way to leverage advanced models like Stable Diffusion for high-quality image generation. Using these pre-built actions, developers can easily integrate image generation capabilities into their applications, enhancing user experiences and expanding creative possibilities.

Prerequisites

Before you start using the akisakurai/stable-karlo Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic understanding of JSON and HTTP requests.

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

Cognitive Actions Overview

Generate Image with Stable Karlo

The Generate Image with Stable Karlo action utilizes the Karlo CLIP image embedding prior and the Stable Diffusion v2.1-768 model to create images based on textual descriptions. This action provides various options for scheduling and noise control to ensure finely detailed outputs.

Input

The input for this action requires the following fields:

  • Seed (optional): Random seed for reproducibility. If left blank, a random seed is generated.
  • Width (required): Width of the output image in pixels. Options range from 128 to 1024 pixels (default is 768).
  • Height (required): Height of the output image in pixels. Options are the same as width.
  • Prompt (required): Text describing the desired image content.
  • Scheduler (optional): Choose a scheduler for the image generation process. Defaults to "K_EULER_ANCESTRAL".
  • Noise Level (optional): Level of noise to add to the image embeddings, affecting texture and detail.
  • Guidance Scale (optional): Controls the strength of classifier-free guidance (default is 7.5).
  • Negative Prompt (optional): Elements to exclude from the output image.
  • Number of Outputs (optional): Number of image outputs to generate (1 to 4).
  • Prior Guidance Scale (optional): Control for the initial classifier-free guidance.
  • Number of Inference Steps (optional): Number of steps for denoising (default is 50).
  • Prior Number of Inference Steps (optional): Initial denoising steps affecting preliminary output structure.
Example Input
{
  "width": 768,
  "height": 768,
  "prompt": "fancy portraits of panda holding vast in laboratory with neon light and blue flame by greg rutkowski, high detail, realistic, concept art, trending on artstation.",
  "scheduler": "K_EULER_ANCESTRAL",
  "guidanceScale": 7.5,
  "negativePrompt": "amateur, mediocre, grainy, blur",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns an array of URLs pointing to the generated images.

Example Output
[
  "https://assets.cognitiveactions.com/invocations/df96d2c4-75f5-4f25-b801-68c7fb734b0a/d1010422-28fa-41ca-8810-12b77fd5672c.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how to call this action using Python. Replace the placeholders with your actual API key and other relevant information.

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 = "5b4eeab4-a626-456b-b99a-a122fea618ff"  # Action ID for Generate Image with Stable Karlo

# Construct the input payload based on the action's requirements
payload = {
    "width": 768,
    "height": 768,
    "prompt": "fancy portraits of panda holding vast in laboratory with neon light and blue flame by greg rutkowski, high detail, realistic, concept art, trending on artstation.",
    "scheduler": "K_EULER_ANCESTRAL",
    "guidanceScale": 7.5,
    "negativePrompt": "amateur, mediocre, grainy, blur",
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 50
}

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 define the action ID and construct the input payload based on the requirements of the Generate Image with Stable Karlo action. The API key and endpoint are placeholders for your actual credentials. This example demonstrates how to send a POST request to the hypothetical Cognitive Actions endpoint to execute the action.

Conclusion

The akisakurai/stable-karlo Cognitive Actions empower developers to create stunning images from text descriptions effortlessly. By utilizing the capabilities of image generation models, these actions can enhance applications in various domains, including gaming, marketing, and art. As you explore these Cognitive Actions, consider experimenting with different prompts and parameters to unlock their full potential. Happy coding!

← Back to All Articles