Transform Your Images into Art: Integrating Watercolor Style with azizakgul/water-color Actions

23 Apr 2025
Transform Your Images into Art: Integrating Watercolor Style with azizakgul/water-color Actions

In the realm of digital art, creating unique and captivating images can be a time-consuming task. The azizakgul/water-color Cognitive Actions provide developers with a seamless way to generate stunning watercolor-style images from prompts and image inputs. By leveraging these pre-built actions, you can enhance your applications with artistic capabilities, allowing users to transform their ideas into beautiful, watercolor-inspired visuals effortlessly.

Prerequisites

Before diving into the integration of the azizakgul/water-color actions, ensure you have the following:

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

Conceptually, you will pass your API key in the headers of your requests to authenticate against the Cognitive Actions services.

Cognitive Actions Overview

Generate Watercolor Style Image

Description: This action generates images in a watercolor painting style based on provided text prompts and optional image masks. It utilizes models optimized for either speed or detailed output, depending on your configuration.

Category: Image Generation

Input

The input schema for this action requires several fields, of which the prompt is mandatory. Here’s a breakdown of the input parameters:

  • prompt (required): A text description guiding the output image.
  • image (optional): A URI for an input image used for inpainting.
  • mask (optional): A URI for a mask image used in inpainting mode.
  • width (optional): Specifies the width of the output image (256-1440).
  • height (optional): Specifies the height of the output image (256-1440).
  • enableFastMode (optional): Boolean to enable faster generation (default: false).
  • inferenceModel (optional): Specifies the model for inference (default: "dev").
  • numberOfOutputs (optional): Number of images to generate (1-4).
  • imageAspectRatio (optional): Aspect ratio of the output image (default: "1:1").
  • imageOutputFormat (optional): Output image format (default: "webp").
  • imageOutputQuality (optional): Quality of output images (0-100).
  • imagePromptStrength (optional): Influence of the prompt in img2img mode (0-1).
  • approximateMegapixels (optional): Approximates the megapixel size.
  • safetyCheckerDisabled (optional): Option to disable safety checks.
  • additionalLoraWeights (optional): Additional LoRA weights to apply.

Example Input:

{
  "image": "https://replicate.delivery/pbxt/M7Y3dZSn30MqvDuqOQ9jMFIRgB1660ZJaOaoqf3ttqQg68DM/970fd0582761297fa02a263420f24645.jpg",
  "prompt": "water color painting of a lizard seen from above in the style of WTRCLR",
  "enableFastMode": false,
  "inferenceModel": "dev",
  "numberOfOutputs": 1,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "imagePromptStrength": 0.8,
  "approximateMegapixels": "1",
  "additionalLoraStrength": 1,
  "diffusionGuidanceScale": 3,
  "inferenceDenoisingSteps": 28,
  "loraApplicationStrength": 1
}

Output

The output of this action will typically return an array of URLs pointing to the generated watercolor-style images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/a40f4aeb-4878-4f6a-b8f8-3dc9977dfd17/90da0385-eafd-40be-a9f5-d4532beb12a3.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Watercolor Style Image 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 = "2ab18f6f-3438-425a-ba1b-8b0239543501"  # Action ID for Generate Watercolor Style Image

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/M7Y3dZSn30MqvDuqOQ9jMFIRgB1660ZJaOaoqf3ttqQg68DM/970fd0582761297fa02a263420f24645.jpg",
    "prompt": "water color painting of a lizard seen from above in the style of WTRCLR",
    "enableFastMode": False,
    "inferenceModel": "dev",
    "numberOfOutputs": 1,
    "imageAspectRatio": "1:1",
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "imagePromptStrength": 0.8,
    "approximateMegapixels": "1",
    "additionalLoraStrength": 1,
    "diffusionGuidanceScale": 3,
    "inferenceDenoisingSteps": 28,
    "loraApplicationStrength": 1
}

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 action_id variable holds the ID of the action you want to invoke. The payload variable contains the necessary input data as defined in the input schema. This example demonstrates how to structure and send a request to the Cognitive Actions service.

Conclusion

The azizakgul/water-color Cognitive Actions empower developers to create artistic transformations of images effortlessly. By integrating these actions into your applications, you open up a world of creative possibilities for users. Whether you want to add a unique flair to user-generated content or create automated artistic outputs, these actions provide a robust solution.

Explore these capabilities further, and consider experimenting with different prompts and configurations to see the diverse range of watercolor images you can create!

← Back to All Articles