Unlocking Image Generation with the Dreamshaper Cognitive Actions

23 Apr 2025
Unlocking Image Generation with the Dreamshaper Cognitive Actions

In the rapidly evolving world of artificial intelligence, generating images from prompts has become a game-changer for developers. The bertagknowles/lcm-dreamshaper8 specification provides powerful Cognitive Actions that enable developers to leverage the Dreamshaper model for fast and customizable image generation. With the ability to specify image dimensions, prompts, and generate multiple images at once, these actions can significantly enhance your applications.

Prerequisites

Before diving into the integration of Cognitive Actions, here are a few prerequisites to get you started:

  • API Key: You will need an API key to authenticate with the Cognitive Actions platform. This key is typically passed in the headers of your API requests.
  • Basic Understanding of JSON: Familiarity with JSON structures will help you format your requests and understand responses.

Conceptually, you will use your API key in the request headers to authenticate your calls to the Cognitive Actions endpoint.

Cognitive Actions Overview

Generate Images with Dreamshaper

Description: This action utilizes the Dreamshaper model to generate images rapidly based on provided prompts. You can customize the image dimensions and specify multiple images to generate simultaneously.

Category: Image Generation

Input

The input schema for the Generate Images with Dreamshaper action is as follows:

  • seed (optional): A random seed for generating images. If not provided, a random seed will be used.
  • width (optional, default: 512): The width of the output image in pixels. You may reduce this if facing memory issues.
  • height (optional, default: 512): The height of the output image in pixels. Similar to width, reduce if necessary.
  • prompt (required): A text prompt that guides the image generation. This defines the thematic and stylistic direction.
  • guidanceScale (optional, default: 0): A scale that affects adherence to the prompt, ranging from 0 to 20.
  • negativePrompt (optional): A prompt specifying undesirable elements to avoid in the generated image.
  • numberOfImages (optional, default: 1): The number of images to generate, ranging from 1 to 50.
  • numberOfInferenceSteps (optional, default: 4): The number of steps for denoising during image generation, recommended between 1 to 8.

Example Input:

{
  "width": 512,
  "height": 512,
  "prompt": "fantacy game ,Illustrate a blue horse against a psychedelic multicolored background ,dramatric lighting, its blue hue a stark contrast to the swirling, vivid colors of the backdrop , The overall effect should be one of movement and energy, capturing the free-spirited essence.",
  "guidanceScale": 0,
  "numberOfImages": 1,
  "numberOfInferenceSteps": 4
}

Output

When you execute this action, the typical output will return a list of URLs pointing to the generated images. For example:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/1014a6e4-d140-4719-8a29-845c16eaf577/7a3860f5-798f-4110-a2d3-99bea1ae7124.jpg"
]

This output contains direct links to the generated images based on your prompt.

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might invoke the Generate Images with Dreamshaper 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 = "397b74c8-b273-4152-b922-268488d4c581" # Action ID for Generate Images with Dreamshaper

# Construct the input payload based on the action's requirements
payload = {
    "width": 512,
    "height": 512,
    "prompt": "fantacy game ,Illustrate a blue horse against a psychedelic multicolored background ,dramatric lighting, its blue hue a stark contrast to the swirling, vivid colors of the backdrop , The overall effect should be one of movement and energy, capturing the free-spirited essence.",
    "guidanceScale": 0,
    "numberOfImages": 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 example, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the Generate Images with Dreamshaper action. The input payload is structured based on the required fields, allowing you to tailor the image generation process.

Conclusion

The Dreamshaper Cognitive Actions offer developers a powerful tool for generating images tailored to specific prompts and dimensions. By integrating these actions into your applications, you can unlock creative possibilities that can enhance user experience and engagement. Explore further use cases, experiment with different prompts, and see how you can elevate your projects using these capabilities!

← Back to All Articles