Create Stunning Art from Text Prompts with Evilstreak's Clipdraw Actions

23 Apr 2025
Create Stunning Art from Text Prompts with Evilstreak's Clipdraw Actions

Introduction

The Evilstreak/Clipdraw API offers an innovative way to generate unique art pieces based on text prompts, leveraging the capabilities of the kvfrans/clipdraw model. By utilizing pre-built Cognitive Actions, developers can effortlessly integrate image generation into their applications, enabling creativity and customization without the need for complex algorithms. These actions provide a powerful tool for artists, game developers, and anyone looking to bring visual concepts to life quickly and effectively.

Prerequisites

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

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with making HTTP requests in your preferred programming language.

For authentication, you will typically pass your API key in the headers of your requests. This acts as a credential to authorize your access to the service.

Cognitive Actions Overview

Generate Art from Text Prompts

  • Description: Create unique art pieces using text prompts with additional constraints for more interesting output. Based on the kvfrans/clipdraw model.
  • Category: Image Generation

Input

The input for this action requires a structured JSON object as specified in the schema:

{
  "prompt": "Watercolor painting of an underwater submarine.",
  "numberOfPaths": 256,
  "displayFrequency": 10,
  "numberOfIterations": 600,
  "distanceFromCenterPower": 2,
  "distanceFromCenterWeight": 0.001,
  "distanceFromCenterThreshold": 75
}
  • Fields:
    • prompt: (string) The main input for image generation. Default is "Watercolor painting of an underwater submarine."
    • numberOfPaths: (integer) Total paths or curves for image generation. Default is 256.
    • displayFrequency: (integer) Interval for displaying intermediate images. Default is 10.
    • numberOfIterations: (integer) Number of iterations for the process. Default is 600.
    • distanceFromCenterPower: (integer) Power affecting distance penalties. Default is 2.
    • distanceFromCenterWeight: (number) Multiplier for distance penalty. Default is 0.001.
    • distanceFromCenterThreshold: (integer) Distance threshold for penalties. Default is 75.

Output

Upon successful execution, the action returns an array of URLs pointing to the generated images, such as:

[
  "https://assets.cognitiveactions.com/invocations/449a51a1-7bb3-4165-94ba-adfe28ae5b62/b9503a05-0706-4bfd-a294-6476f655c023.png",
  "https://assets.cognitiveactions.com/invocations/449a51a1-7bb3-4165-94ba-adfe28ae5b62/c939b00d-d29d-4d0b-bb5e-9d52ce9dd1c7.png",
  ...
]

These URLs link to the generated images, allowing you to display or utilize them as needed.

Conceptual Usage Example (Python)

Here’s how you might structure a Python code snippet to invoke this 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 = "2d14f360-d785-402a-96f3-3e5149ffb83b"  # Action ID for Generate Art from Text Prompts

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "Watercolor painting of an underwater submarine.",
    "numberOfPaths": 256,
    "displayFrequency": 10,
    "numberOfIterations": 600,
    "distanceFromCenterPower": 2,
    "distanceFromCenterWeight": 0.001,
    "distanceFromCenterThreshold": 75
}

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:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The payload variable contains the structured input needed for the action.
  • The action_id corresponds to the "Generate Art from Text Prompts" action.
  • The endpoint URL and request structure are hypothetical; adapt them based on your specific API documentation.

Conclusion

The Evilstreak/Clipdraw Cognitive Actions provide an exciting opportunity to generate images from text prompts seamlessly. By understanding how to structure your inputs and handle outputs, you can integrate powerful image generation capabilities into your applications. Explore creative use cases, experiment with different prompts and parameters, and unleash your artistic potential!

← Back to All Articles