image-generation

Create Stunning Images with Sood Image's Inpainting Feature

26 Apr 2025
Create Stunning Images with Sood Image's Inpainting Feature

In the world of digital content creation, the ability to generate high-quality images quickly and efficiently is invaluable. Sood Image provides developers with powerful Cognitive Actions that simplify the image generation process through advanced inpainting and img2img capabilities. By harnessing customizable parameters, developers can create visually appealing images tailored to specific needs, making it an essential tool for various applications such as marketing, gaming, and content creation.

Common use cases for Sood Image include generating unique visuals for social media campaigns, designing assets for video games, or even enhancing existing images by filling in gaps or modifying specific areas. With its intuitive parameters, Sood Image empowers developers to produce stunning images that captivate audiences while saving time and effort.

Before getting started, ensure you have a Cognitive Actions API key and a basic understanding of making API calls.

Generate Image with Inpainting

The "Generate Image with Inpainting" action allows you to create images using either img2img or inpainting modes. This action is particularly beneficial when you want to modify an existing image or fill in specific areas while preserving other parts. It supports a wide range of configurable parameters, enabling high customization for image generation.

Input Requirements

To utilize this action effectively, you need to provide several inputs:

  • Mask: A URI pointing to an input mask for inpainting mode where black areas are preserved, and white areas are inpainted.
  • Seed: An optional random seed value for consistent results.
  • Image: A URI of the input image for processing.
  • Width and Height: Specify the dimensions of the output image, with a default of 1024 pixels.
  • Prompt: A descriptive text input to guide the image generation process.
  • Refinement Method: Choose a refinement style for enhancing the image.
  • Scheduler: Select an algorithm for image generation scheduling.
  • Guidance Scale: A factor for classifier-free guidance, ranging from 1 to 50.
  • Negative Prompt: Input for specifying undesirable features in the generated image.
  • Number of Outputs: Define how many images to generate (1 to 4).
  • Prompt Intensity: Control the strength of the prompt's influence.
  • Watermark Enabled: Option to apply watermarking on generated images.

Expected Output

The expected output is a generated image based on the provided inputs. For example, a successful request could return a URI link to the newly created image.

Use Cases for this specific action

This action is perfect for various scenarios:

  • Marketing: Generate unique visuals for advertisements or social media posts.
  • Content Creation: Create illustrations for blogs, articles, or digital publications.
  • Game Development: Design and modify assets in real-time, enhancing the visual appeal of gaming environments.

Here’s a placeholder for your code snippet:

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 = "5fc2df93-2258-45bf-a10c-2143e229e9ff" # 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 = {
  "width": 1024,
  "height": 1024,
  "prompt": "airplane taking off from an airport in iowa",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "loraIntensity": 0.6,
  "negativePrompt": "",
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "watermarkEnabled": true,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 50
}

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

Sood Image's inpainting feature provides developers with an efficient way to generate and modify images to meet specific requirements. With its customizable parameters and robust capabilities, this action can significantly enhance your creative projects, whether you're in marketing, content creation, or game development. Start integrating Sood Image into your workflow today and unlock the potential for stunning visual content.

← Back to All Articles