Create Stunning Custom Images with the Eddie87/Mollywade Cognitive Actions

22 Apr 2025
Create Stunning Custom Images with the Eddie87/Mollywade Cognitive Actions

In today's digital landscape, generating captivating images programmatically has become a vital skill for developers. The Eddie87/Mollywade API offers powerful Cognitive Actions that allow you to create customized images using detailed text prompts. This capability not only saves time but also empowers developers to produce high-quality visuals tailored to specific needs. In this article, we'll explore how to integrate the "Generate Custom Image" action into your applications, allowing you to bring your creative visions to life.

Prerequisites

Before diving into the integration, make sure you have the following prerequisites in place:

  • API Key: You will need an API key to authenticate your requests to the Cognitive Actions platform. This key is typically passed as a header in your requests.
  • Basic Understanding of JSON: Familiarity with JSON will help you structure your input and interpret the output efficiently.

Cognitive Actions Overview

Generate Custom Image

The Generate Custom Image action is designed to create customized images based on a provided text prompt. It supports various modes including inpainting and image-to-image (img2img), allowing for extensive control over the generated output, such as dimensions, quality, and model type.

Input

The input for this action is defined in a JSON schema, which includes several required and optional fields:

  • Required Fields:
    • prompt: The text prompt guiding the image generation.
  • Optional Fields:
    • mask: Image mask for inpainting mode.
    • seed: Random seed for reproducibility.
    • image: Input image for img2img mode.
    • width: Width of the generated image.
    • height: Height of the generated image.
    • modelType: Selects the model for inference, either "dev" or "schnell".
    • outputCount: Number of output images to generate (between 1 and 4).
    • And many more...

Example Input

Here’s an example of the JSON payload you would use to invoke this action:

{
  "width": 1440,
  "height": 1440,
  "prompt": "Molly_W soars through the sky, her blue-and-red suit emblazoned with a shining 'S' crest on her chest. Her blonde hair flows wildly in the wind, and her cape billows behind her, streaked with gold trim. Eyes glowing with power, she channels heat vision. The setting is a futuristic cityscape at dusk, skyscrapers gleaming in twilight. The scene features high-contrast lighting with golden rays reflecting off glass buildings. In cinematic realism, the shallow depth of field centers on Molly_W in flight, leaving the cityscape blurred, enhancing her dynamic movement and power.",
  "modelType": "dev",
  "outputCount": 1,
  "loraIntensity": 1,
  "denoisingSteps": 28,
  "promptIntensity": 0.8,
  "imageAspectRatio": "16:9",
  "imageOutputFormat": "webp",
  "imageGuidanceScale": 3.5,
  "imageOutputQuality": 90,
  "additionalLoraIntensity": 1
}

Output

When the action is successfully executed, it returns a URL pointing to the generated image:

[
  "https://assets.cognitiveactions.com/invocations/2048d35f-4bb5-46ca-bdae-6defab694a31/ba085b3b-b2f8-4c62-a6a5-20a9f3ac9c0a.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how you could implement this action in Python. This code snippet demonstrates how to structure the input JSON payload and make the API call:

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 = "29f35734-fe92-4bf1-b5a0-93e36812cb01"  # Action ID for Generate Custom Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1440,
    "height": 1440,
    "prompt": "Molly_W soars through the sky, her blue-and-red suit emblazoned with a shining 'S' crest on her chest. Her blonde hair flows wildly in the wind...",
    "modelType": "dev",
    "outputCount": 1,
    "loraIntensity": 1,
    "denoisingSteps": 28,
    "promptIntensity": 0.8,
    "imageAspectRatio": "16:9",
    "imageOutputFormat": "webp",
    "imageGuidanceScale": 3.5,
    "imageOutputQuality": 90,
    "additionalLoraIntensity": 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 example, replace "YOUR_COGNITIVE_ACTIONS_API_KEY" with your actual API key. The payload variable is constructed based on the requirements of the "Generate Custom Image" action, and the script posts this payload to the hypothetical endpoint.

Conclusion

The Eddie87/Mollywade Cognitive Actions provide a robust solution for developers looking to generate custom images effortlessly. By leveraging the "Generate Custom Image" action, you can create stunning, tailored visuals that enhance your applications. Start experimenting with different prompts and configurations to see what unique images you can create! Happy coding!

← Back to All Articles