image-generation

Create Stunning Images with Ivet's Inpainting Action

26 Apr 2025
Create Stunning Images with Ivet's Inpainting Action

In today's fast-paced digital landscape, developers are constantly seeking ways to enhance their applications with rich, engaging visuals. Ivet offers a powerful Cognitive Action that allows you to generate images using advanced inpainting techniques. This functionality not only simplifies the image creation process but also provides customizable parameters, enabling you to tailor outputs to specific needs. Whether you're building a creative app, enhancing a website, or developing content for marketing campaigns, Ivet's inpainting capabilities can significantly elevate the visual quality of your projects.

Imagine a scenario where you need to create a stunning visual for a blog post or social media campaign. Instead of sourcing images from stock libraries, you can generate unique, high-quality images that align perfectly with your content. This not only saves time but also allows for greater creativity and originality in your work.

Prerequisites

To get started with Ivet's Cognitive Actions, you'll need an API key and a basic understanding of making API calls. This will enable you to seamlessly integrate the image generation capabilities into your applications.

Generate Image with Inpainting

The Generate Image with Inpainting action is designed to create images by filling in or modifying specific areas based on a provided mask. This operation supports various customizable options, including image dimensions, output formats, and quality settings.

Purpose

This action allows developers to solve the problem of generating high-quality images that fit specific requirements. By leveraging inpainting, you can create detailed visuals that align with your vision without relying on pre-existing images.

Input Requirements

The input for this action is structured as an object, requiring a prompt to guide the image generation:

  • Prompt: A descriptive text that guides the image creation (e.g., "A highly realistic man looking to the camera").
  • Mask: (Optional) An image mask for inpainting mode.
  • Image: (Optional) An existing image for modification.
  • Width and Height: Define the dimensions for the output image (only for 'custom' aspect ratios).
  • Output Format: Specify the desired image format (e.g., jpg, png).
  • Guidance Scale: Control the level of adherence to the prompt during generation.
  • Number of Outputs: Set how many images to generate in one request (up to 4).

Expected Output

The expected output is a URL link to the generated image, allowing for easy access and integration into your projects. For example, the output might look like this:

https://assets.cognitiveactions.com/invocations/8dd4e5f5-f185-4726-92d8-b5e6b6de5c1d/4b2534ca-18cb-4557-8995-45639861fce4.jpg

Use Cases for this Specific Action

  1. Content Creation: Generate unique visuals for blog posts, articles, and social media without relying on stock images.
  2. Marketing Campaigns: Create tailored images that resonate with your target audience, enhancing engagement and brand identity.
  3. UI/UX Design: Produce high-quality images for applications, websites, or prototypes, allowing for rapid design iterations.
  4. Artistic Projects: Enable artists and designers to experiment with concepts and styles, generating visuals that may not be easily achievable through traditional methods.
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 = "b068924e-1875-49fc-9eb9-c17e47b4ec04" # 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 = {
  "prompt": "ivet  A highly realistic man looking to the camera",
  "outputFormat": "jpg",
  "guidanceScale": 3,
  "mainLoraScale": 1,
  "outputQuality": 80,
  "selectedModel": "dev",
  "enableFastMode": false,
  "megapixelCount": "1",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageAspectRatio": "16:9",
  "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

Ivet's inpainting action presents a robust solution for developers looking to enhance their applications with unique, high-quality images. By simplifying the image generation process and offering extensive customization options, Ivet empowers creatives to produce visuals that are not only captivating but also aligned with their specific needs.

As you explore the capabilities of Ivet, consider how these image generation functions can be integrated into your projects to enhance user experience and engagement. With Ivet, the possibilities for creative expression are limitless.

← Back to All Articles