Generate Stunning Images with the prunaai/stable-diffusion-turbo Actions

23 Apr 2025
Generate Stunning Images with the prunaai/stable-diffusion-turbo Actions

In the world of artificial intelligence, image generation has taken a significant leap forward with the advent of models like Stable Diffusion. The prunaai/stable-diffusion-turbo API offers developers the ability to harness an optimized version of Stable Diffusion from Stability AI, enabling them to generate high-quality images from textual descriptions efficiently. This not only enhances creative possibilities but also provides a cost-effective solution for developers looking to integrate image generation capabilities into their applications.

Prerequisites

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

  • An API key for accessing the Cognitive Actions platform.
  • Basic familiarity with making API calls using JSON.
  • A development environment set up for making HTTP requests (Python is used in this example).

Authentication typically involves passing your API key in the headers of your requests, which will be demonstrated in the examples below.

Cognitive Actions Overview

Generate Optimized Image with Stable Diffusion

The Generate Optimized Image with Stable Diffusion action allows you to create images based on textual prompts using an optimized model that runs efficiently on T4 GPUs.

  • Category: Image Generation

Input

The input for this action requires a JSON object that includes the following fields:

  • prompt (required): A textual description of the image to be generated (e.g., "a red apple on a table").
  • seed (optional): An integer to initialize the random number generator for reproducible results (default is 42).
  • imageWidth (optional): The width of the output image in pixels (default is 512).
  • imageHeight (optional): The height of the output image in pixels (default is 512).
  • guidanceScale (optional): A scaling factor that influences adherence to the prompt (default is 7.5).
  • numberOfImages (optional): The number of images to generate (default is 1).
  • numberOfInferenceSteps (optional): The number of inference steps for image generation (default is 50).

Example Input:

{
  "seed": 0,
  "prompt": "a red apple on a table",
  "imageWidth": 512,
  "imageHeight": 512,
  "guidanceScale": 7.5,
  "numberOfImages": 1,
  "numberOfInferenceSteps": 50
}

Output

Upon successful execution, this action returns a URL pointing to the generated image. For example:

https://assets.cognitiveactions.com/invocations/4c2720ee-b1fa-43ef-a871-ba6af788e041/1744b22d-65e2-4945-86f9-8f68825be63b.png

This URL can be accessed directly to view or download the generated image.

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet demonstrating how to call the Generate Optimized Image with Stable Diffusion 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 = "ebff20c7-2d6c-4839-a1b0-b8ca1b3a338d"  # Action ID for Generate Optimized Image with Stable Diffusion

# Construct the input payload based on the action's requirements
payload = {
    "seed": 0,
    "prompt": "a red apple on a table",
    "imageWidth": 512,
    "imageHeight": 512,
    "guidanceScale": 7.5,
    "numberOfImages": 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, you’ll see how to structure the input JSON payload, replace the action ID, and handle the API response. The endpoint URL and request structure are illustrative, focusing on how to effectively use the action.

Conclusion

The prunaai/stable-diffusion-turbo actions provide developers with powerful tools for image generation, making it easier to transform textual prompts into stunning visuals. With an optimized architecture and straightforward API calls, integrating these actions into your applications can unlock new creative potentials.

Consider exploring various prompts and settings to see the diverse outputs you can achieve, and think about how these capabilities could enhance your projects or services. Happy coding!

← Back to All Articles