image-generation

Create Stunning Images with Inpainting Using Billy

25 Apr 2025
Create Stunning Images with Inpainting Using Billy

In the world of digital content creation, generating high-quality images can be a daunting task, especially when it involves intricate details or specific visual elements. Billy's "Generate Image with Inpainting" action simplifies this process by allowing developers to create images through advanced inpainting techniques. By leveraging input prompts and image masks, this action enables the generation of unique visuals tailored to specific requirements. With options for model selection and performance optimizations, developers can achieve stunning results efficiently.

This action opens up a wide array of use cases, from enhancing existing images to creating entirely new compositions. Whether you're a game developer looking to generate character art, a marketer needing custom visuals for campaigns, or a content creator wanting to produce eye-catching graphics, Billy’s inpainting feature can help streamline your workflow. The ability to handle various output formats and customize parameters makes it a versatile tool for any developer.

Prerequisites

To get started, you'll need an API key for Billy's Cognitive Actions and a basic understanding of how to make API calls.

Generate Image with Inpainting

The "Generate Image with Inpainting" action is designed to create new images by applying sophisticated inpainting techniques. This action allows you to specify a prompt, use an image mask, and select different models based on your performance needs. It addresses the common challenge of generating high-quality images that meet specific artistic requirements.

Input Requirements

To use this action, you'll need to provide a structured input object that includes:

  • prompt (required): A descriptive string that guides the image generation.
  • mask (optional): An image mask for inpainting, which, if provided, will override aspect ratio, width, and height inputs.
  • image (optional): An input image for inpainting or image-to-image transformations.
  • model: Choose between 'dev' for detailed results or 'schnell' for faster output.
  • width and height: Dimensions for the generated image (only applicable if aspect ratio is set to custom).
  • Additional parameters like loraScale, guidanceScale, outputQuality, and numberOfInferenceSteps to fine-tune the output.

Expected Output

The expected output is a URL pointing to the generated image in the specified format. This allows for easy integration into your applications or websites.

Use Cases for this Specific Action

  • Game Development: Create unique character designs or environmental art based on specific themes or concepts.
  • Marketing Materials: Generate custom visuals that align with brand aesthetics for advertisements or social media.
  • Content Creation: Produce bespoke images that enhance storytelling in blogs, videos, or presentations.

By utilizing the inpainting action, developers can enhance their creative capabilities while saving time and resources.

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 = "ec3b5d26-2abe-4193-986b-b3992c143af4" # Action ID for: Generate 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",
  "width": 1024,
  "height": 1024,
  "prompt": "Closeup portrait of cyber-mage BILLMUSH is surrounded by magical sigils that have a retro sci-fi tech style. He looks confident in his knowledge of magic. Posing dynamically. Cinematic movie still.",
  "loraScale": 1,
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "png",
  "additionalLoraScale": 1,
  "numberOfInferenceSteps": 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

Billy's "Generate Image with Inpainting" action offers developers a powerful tool for creating visually captivating images tailored to their specific needs. With the ability to customize inputs and optimize for performance, this action simplifies the image generation process, making it accessible to a wide range of applications. Whether you are looking to enhance existing visuals or create new ones from scratch, Billy provides the flexibility and efficiency needed to bring your ideas to life. Start integrating this action into your projects today to unlock new creative possibilities!

← Back to All Articles