Generate Stunning Images with the sofoo1992/sd21 Cognitive Actions

23 Apr 2025
Generate Stunning Images with the sofoo1992/sd21 Cognitive Actions

In the world of digital creation, the ability to generate images based on textual prompts has opened up a realm of possibilities for developers and creative minds alike. The sofoo1992/sd21 Cognitive Actions provide a powerful API for generating images using user-defined prompts and customizable parameters. By utilizing these pre-built actions, developers can seamlessly integrate image generation capabilities into their applications, thereby enhancing user engagement and creativity.

Prerequisites

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

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of making HTTP requests in your preferred programming language.

For authentication, you will typically pass your API key in the request headers.

Cognitive Actions Overview

Generate Image Based on Prompt

The Generate Image Based on Prompt action allows you to create an image from a user-defined prompt. You can customize various parameters such as image dimensions, the number of outputs, and the guidance scale using the sd21 model. This action is particularly useful for applications requiring dynamic image generation based on user input.

Category: image-generation

Input

The input for this action requires the following fields in JSON format:

  • seed (integer, optional): Random seed to initialize the random number generator. Leave blank for a randomized seed.
  • width (integer, optional): Width of the output image. Choose from preset values (512, 576, ..., 1024). Default is 768.
  • height (integer, optional): Height of the output image. Choose from preset values (512, 576, ..., 1024). Default is 768.
  • prompt (string, required): The description of the desired content for the generated image. Default is "a photo of an astronaut riding a horse on mars".
  • scheduler (string, optional): Selects the scheduler for the generation process. Default is "DPMSolverMultistep".
  • guidanceScale (number, optional): Scale for classifier-free guidance affecting adherence to the prompt. Range is 1 to 20, default is 7.5.
  • negativePrompt (string, optional): Elements to exclude from the output image.
  • numberOfOutputs (integer, optional): Number of images to generate (1 to 4). Default is 1.
  • numberOfInferenceSteps (integer, optional): Number of steps used in the denoising process (1 to 500). Default is 50.

Example Input:

{
  "seed": 8899,
  "width": 768,
  "height": 768,
  "prompt": "a photo of an astronaut riding a horse on mars",
  "scheduler": "DPMSolverMultistep",
  "guidanceScale": 7.5,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Output

The action typically returns an array containing the URLs of the generated images. Each URL points to a specific image created based on the provided input prompt.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/ca2c7b20-faa0-4bd2-8c39-3002111d0975/1d11f64c-3749-4c91-bace-1a82e0db467f.png"
]

Conceptual Usage Example (Python)

Here's a conceptual example of how you might use this action in Python to generate an image based on a prompt:

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 = "cadad7c9-4c66-41da-8e25-78c5483d5262"  # Action ID for Generate Image Based on Prompt

# Construct the input payload based on the action's requirements
payload = {
    "seed": 8899,
    "width": 768,
    "height": 768,
    "prompt": "a photo of an astronaut riding a horse on mars",
    "scheduler": "DPMSolverMultistep",
    "guidanceScale": 7.5,
    "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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is populated with the required input parameters for generating an image. This illustrates how to structure the input JSON payload and make a POST request to the hypothetical Cognitive Actions API.

Conclusion

The sofoo1992/sd21 Cognitive Actions provide a robust solution for integrating image generation capabilities into your applications. By leveraging features such as customizable prompts, dimensions, and guidance scales, developers can create dynamic visual content that enhances user experience. Start experimenting with these actions to unlock new creative possibilities in your projects!

← Back to All Articles