image-generation

Create Unique Images Effortlessly with Puffs Cognitive Actions

25 Apr 2025
Create Unique Images Effortlessly with Puffs Cognitive Actions

In the rapidly evolving world of digital content, the ability to generate custom images can significantly enhance user engagement and creativity. Puffs offers a powerful set of Cognitive Actions designed to help developers create unique images with ease. With features such as inpainting and custom dimensions, Puffs not only streamlines the image generation process but also ensures high-quality outputs tailored to specific needs. Whether you're building an application for digital marketing, art, or social media, these actions can simplify your workflow and elevate your creative projects.

Prerequisites

To get started with Puffs, you'll need a Cognitive Actions API key and a basic understanding of API calls. This will allow you to access the functionalities and integrate them into your applications effectively.

Generate Custom Image with Inpainting

The "Generate Custom Image with Inpainting" action enables you to create custom images using either image-to-image transformation or inpainting modes. This action is particularly beneficial for developers looking to produce high-quality visuals quickly, offering customizable dimensions, aspect ratios, and various output formats.

Input Requirements

To utilize this action, you must provide a prompt that guides the image generation. Additionally, you can include parameters like an image for transformation, a mask for inpainting, and various other settings like aspect ratio, output format, and more.

Expected Output

The output will be a custom image generated based on your specifications. The action supports multiple output formats, including webp, jpg, and png, ensuring that you can choose the best fit for your application.

Use Cases for this specific action

  • Marketing Campaigns: Generate eye-catching visuals tailored to specific themes or products.
  • Art Projects: Create unique art pieces or illustrations based on custom prompts, enabling artists to explore new styles.
  • Social Media Content: Quickly produce engaging images that resonate with target audiences, enhancing social media strategies.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "aef3a604-897e-4944-a22a-a5a57f0ee96a" # Action ID for: Generate Custom Image with Inpainting

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "model": "dev",
  "prompt": "in the style of puff, a puff person with lots of jewelry driving a yellow Ferrari on the highway",
  "loraScale": 1,
  "aspectRatio": "1:1",
  "outputCount": 1,
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "inferenceStepCount": 28
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Puffs' Cognitive Actions provide an intuitive and efficient way for developers to generate custom images tailored to their needs. With the ability to create high-quality visuals quickly, these actions are perfect for a wide range of applications, from marketing to art projects. As you explore the capabilities of Puffs, consider how you can integrate these actions into your workflows to enhance creativity and productivity. Start experimenting today and unlock the full potential of image generation with Puffs!

← Back to All Articles