image-processing

Effortlessly Customize Facial Expressions with the Expression Editor

26 Apr 2025
Effortlessly Customize Facial Expressions with the Expression Editor

The Expression Editor offers developers a powerful tool for manipulating facial expressions in images, allowing for dynamic and nuanced adjustments. With this service, you can easily modify expressions to suit your creative needs, whether for marketing materials, social media content, or entertainment applications. The benefits of using the Expression Editor include rapid adjustments, enhanced user engagement, and the ability to create personalized visuals that resonate with audiences.

Common use cases for the Expression Editor include enhancing character animations in gaming, creating personalized avatars for virtual reality, or simply adding a touch of humor or emotion to photos. The ability to fine-tune facial expressions can significantly improve storytelling and audience connection in various media formats.

Before diving in, ensure you have a Cognitive Actions API key and a basic understanding of making API calls to get started with the Expression Editor.

Edit Facial Expression

The Edit Facial Expression action allows you to effortlessly adjust and customize various facial expressions in an image using the LivePortrait model. This action solves the problem of static images that lack emotional depth, enabling developers to bring images to life with customizable expressions.

Input Requirements

To use this action, you will need to provide a valid image URL along with specific parameters that control the facial features, such as:

  • Wink: Controls the degree of one eye closure (0 to 25).
  • Blink: Adjusts the degree of both eyes closing or opening wider (-20 to 5).
  • Smile: Modifies the degree of smiling (-0.3 to 1.3).
  • Eyebrow: Adjusts the height and shape of the eyebrows (-10 to 15).
  • Rotation Yaw: Adjusts the left and right rotation of the face (-20 to 20).
  • Output Format: Specifies the format of the output images (webp, jpg, png).
  • Additional parameters include mouth shapes, pupil positions, and output quality.

Expected Output

The action will return a modified image with the specified adjustments applied. The output is a URL pointing to the newly generated image, allowing for easy integration into your applications.

Example Input:

{
  "wink": 0,
  "blink": 0,
  "image": "https://replicate.delivery/pbxt/Lg7pzAsHjoZlGHtrfI4wnVZchV8G9XCyXXMG37YMyb4NoBiU/PhotoMaker_00001_.png",
  "smile": 0,
  "eyebrow": 0,
  "rotationYaw": 0,
  "sourceRatio": 1,
  "mouthOpenAaa": 0,
  "outputFormat": "webp",
  "rotationRoll": 0,
  "mouthShapeEee": 0,
  "mouthShapeWoo": 0,
  "outputQuality": 95,
  "rotationPitch": 10.54,
  "croppingCoefficient": 1.7,
  "samplingCoefficient": 1,
  "pupilPositionVertical": 0,
  "pupilPositionHorizontal": 13.46
}

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/42887191-916a-4243-a54d-70ed1a1668f5/4c5c0159-0010-4785-b4f3-9833754378af.webp"
]

Use Cases for this Specific Action

This action is ideal for a variety of scenarios:

  • Marketing Campaigns: Create engaging visuals that capture attention by adjusting facial expressions to match the message.
  • Social Media Content: Generate unique and expressive images that stand out in crowded feeds, increasing shares and likes.
  • Game Development: Enhance character interactions by allowing for real-time expression changes, improving player immersion.
  • Personalized Avatars: Enable users to create avatars that reflect their emotions, enhancing user experience in virtual environments.

```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 = "0098db82-a80c-4d25-8ebf-f83508061601" # Action ID for: Edit Facial Expression

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "wink": 0,
  "blink": 0,
  "image": "https://replicate.delivery/pbxt/Lg7pzAsHjoZlGHtrfI4wnVZchV8G9XCyXXMG37YMyb4NoBiU/PhotoMaker_00001_.png",
  "smile": 0,
  "eyebrow": 0,
  "rotationYaw": 0,
  "sourceRatio": 1,
  "mouthOpenAaa": 0,
  "outputFormat": "webp",
  "rotationRoll": 0,
  "mouthShapeEee": 0,
  "mouthShapeWoo": 0,
  "outputQuality": 95,
  "rotationPitch": 10.54,
  "croppingCoefficient": 1.7,
  "samplingCoefficient": 1,
  "pupilPositionVertical": 0,
  "pupilPositionHorizontal": 13.46
}

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, the Expression Editor provides developers with a robust solution for customizing facial expressions in images. With its wide range of adjustable parameters, you can create dynamic visuals that enhance storytelling and engage audiences. Whether you're working on marketing materials, gaming, or social media content, integrating the Expression Editor into your workflow can elevate your creative projects. 

As a next step, consider experimenting with different parameters to see how they impact the final output. This exploration can lead to innovative applications and more engaging user experiences.
← Back to All Articles