image-processing

Create Stunning Masked Images Easily with Owl Sam

27 Apr 2025
Create Stunning Masked Images Easily with Owl Sam

Owl Sam is an innovative service designed to simplify image processing tasks for developers. With its powerful Cognitive Actions, you can easily manipulate images, allowing for advanced functionalities like object detection and masking. This capability not only streamlines your workflow but also enhances the quality of your visual content. Whether you’re building applications for fashion, advertising, or any field that requires image analysis, Owl Sam provides the tools you need to create engaging visual experiences quickly and efficiently.

One of the standout features of Owl Sam is the ability to generate masked images using the OwlV2 model. This feature is particularly useful in scenarios where you want to highlight specific objects within an image while obscuring the rest. For example, in e-commerce, you might want to focus on clothing items while masking the background to draw customer attention. Additionally, the flexibility to customize detection thresholds allows developers to fine-tune the object detection process based on their specific needs.

Generate Masked Image with OwlV2

The "Generate Masked Image with OwlV2" action allows you to create masked images by applying object detection. This operation works by taking a URI pointing to an image resource and applying custom mask prompts, which can be tailored to your requirements. The ability to set a detection threshold further enhances the precision of the object detection process.

Input Requirements

To use this action, you need to provide:

  • Image: A URI pointing to the image resource (e.g., a URL). The default example points to a fashion outfit image.
  • Mask Prompts: An array of strings that serves as prompts for mask creation. Each prompt must end with a period (e.g., "face.").
  • Detection Threshold: A number ranging from 0 to 1 that sets the cutoff for object detection. The default is set to 0.3, but lower values can be used to trigger more detections.

Example Input:

{
  "image": "https://st.mngbcn.com/rcs/pics/static/T5/fotos/outfit/S20/57034757_56-99999999_01.jpg",
  "maskPrompts": [
    "shoes",
    "pants"
  ],
  "detectionThreshold": 0.15
}

Expected Output

The expected output will be an array of URLs pointing to the newly generated masked images, showcasing the specified objects based on your prompts.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/dd2167cc-1585-4904-8b3d-600736d6ca78/773acb28-f7bd-4e73-87d8-b59f460f6e53.jpg",
  "https://assets.cognitiveactions.com/invocations/dd2167cc-1585-4904-8b3d-600736d6ca78/37959858-0b89-4621-a21c-162e6634314e.jpg",
  "https://assets.cognitiveactions.com/invocations/dd2167cc-1585-4904-8b3d-600736d6ca78/eadbebc3-8073-467a-a289-7ff50e15685b.jpg"
]

Use Cases for this Action

  • E-commerce Platforms: Highlight specific clothing items while masking the background to improve customer focus.
  • Marketing Campaigns: Create promotional graphics that emphasize particular products or features in an image.
  • Content Creation: Generate unique visuals for social media posts by masking unwanted elements and focusing on the subject matter.

```python
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 = "8c73c20b-0c1d-436e-a405-324317f08975" # Action ID for: Generate Masked Image with OwlV2

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "image": "https://st.mngbcn.com/rcs/pics/static/T5/fotos/outfit/S20/57034757_56-99999999_01.jpg",
  "maskPrompts": [
    "shoes",
    "pants"
  ],
  "detectionThreshold": 0.15
}

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("------------------------------------------------")



In conclusion, Owl Sam's Cognitive Actions offer developers a powerful way to enhance image processing capabilities. The ability to generate masked images with precision can elevate visual content across various applications, making it a valuable tool for anyone involved in digital media. To get started, ensure you have your Cognitive Actions API key and familiarize yourself with the API call structure. Then, unleash your creativity by integrating these actions into your projects to deliver stunning visual experiences.
← Back to All Articles