Create Stunning Images Effortlessly with Buzzfeed's Drake Test Cognitive Actions

22 Apr 2025
Create Stunning Images Effortlessly with Buzzfeed's Drake Test Cognitive Actions

In today's digital landscape, the demand for high-quality images is ever-growing, whether for marketing campaigns, social media, or content creation. The Buzzfeed/Drake Test offers a powerful Cognitive Action that allows developers to generate enhanced images through advanced image generation techniques. This capability not only helps automate the creation of visuals but also provides customization options to refine the output to meet specific needs.

In this article, we'll explore how to leverage the Generate Enhanced Images action to create stunning visuals in your applications.

Prerequisites

Before you start integrating the Buzzfeed Drake Test Cognitive Actions, you'll need the following:

  • An API key from the Cognitive Actions platform to authenticate your requests.
  • Familiarity with JSON structures, as you'll be sending and receiving data in this format.

Authentication typically involves passing your API key in the headers of your requests, allowing secure access to the action endpoints.

Cognitive Actions Overview

Generate Enhanced Images

The Generate Enhanced Images action is designed to create high-quality images based on your input prompts. It supports inpainting and img2img modes, offering refinement options for enhanced image quality and customization. This action falls under the image-generation category.

Input

The action requires a JSON payload that includes various fields:

  • mask (optional): A URI pointing to the input mask for inpaint mode.
  • seed (optional): An integer seed number to ensure consistency in image generation.
  • image (optional): A URI pointing to the input image for img2img or inpaint mode.
  • width (optional, default: 1024): Width in pixels for the output image.
  • height (optional, default: 1024): Height in pixels for the output image.
  • prompt (required): A descriptive text prompt guiding the image generation.
  • refine (optional, default: "no_refiner"): Selects the refinement style.
  • weights (optional): LoRA weights for generation.
  • loraScale (optional, default: 0.6): Scale factor for LoRA's effect.
  • scheduler (optional, default: "K_EULER"): Algorithm for scheduling image generation steps.
  • guidanceScale (optional, default: 7.5): Influences classifier-free guidance strength.
  • applyWatermark (optional, default: true): Whether to apply a watermark to the images.
  • negativePrompt (optional): Specifies elements to avoid in the image.
  • promptStrength (optional, default: 0.8): Influences prompt impact in img2img or inpaint mode.
  • numberOfOutputs (optional, default: 1): Number of images to generate (1-4).
  • numberOfInferenceSteps (optional, default: 50): Total denoising steps during image generation.

Here's an example of the JSON input you might use:

{
  "width": 1024,
  "height": 1024,
  "prompt": "an elephant, an abstract drawing by a child in the style of TOK, black background, black and white crayon",
  "refine": "no_refiner",
  "loraScale": 1,
  "scheduler": "K_EULER",
  "guidanceScale": 13,
  "applyWatermark": false,
  "negativePrompt": "blurry, low quality",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}

Output

Upon successful execution, the action returns a JSON response containing URLs to the generated images. Here's an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/6cd2fc45-9d1b-4bef-a4c5-e4506c410005/5abffc28-ac60-487b-b39f-3a7431c1932d.png"
]

Conceptual Usage Example (Python)

Below is a conceptual example demonstrating how you could call the Generate Enhanced Images 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 = "9d64b439-a5e9-4d94-851a-bfd5e463735c"  # Action ID for Generate Enhanced Images

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "an elephant, an abstract drawing by a child in the style of TOK, black background, black and white crayon",
    "refine": "no_refiner",
    "loraScale": 1,
    "scheduler": "K_EULER",
    "guidanceScale": 13,
    "applyWatermark": False,
    "negativePrompt": "blurry, low quality",
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "highNoiseFraction": 0.8,
    "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 the above code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable includes the required input for the action, and the API call is structured according to the Cognitive Actions requirements.

Conclusion

The Generate Enhanced Images action from the Buzzfeed/Drake Test provides a robust solution for developers looking to create high-quality, customized images programmatically. With its array of parameters, you can tailor the output to fit specific needs, making it an invaluable tool for content creators and businesses alike.

Consider exploring additional use cases, such as generating images for product marketing, enhancing social media content, or creating unique visuals for blogs. Dive in and start creating stunning images today!

← Back to All Articles