image-generation

Create Stunning Images from Faces with Pulid Base

25 Apr 2025
Create Stunning Images from Faces with Pulid Base

In the world of image generation, the ability to create high-quality visuals from a simple reference image can transform how developers approach creative projects. Pulid Base provides a powerful Cognitive Action that allows you to generate images based on a face image, utilizing advanced models fine-tuned for various styles and formats. This service not only streamlines the image creation process but also enhances the potential for creative expression, making it an invaluable tool for developers in fields such as gaming, advertising, and social media.

Imagine a scenario where you need to create a unique character for a game or an engaging promotional image for a marketing campaign. Instead of relying on stock images or manual illustrations, you can leverage Pulid Base to generate custom images that meet your specific requirements. Whether you need a high-fidelity portrait or a stylized anime character, this service simplifies the process, enabling you to focus more on creativity and less on technical hurdles.

Prerequisites

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

Generate Image from Face

The "Generate Image from Face" action allows developers to create images using a face image as a reference. This action utilizes SDXL fine-tuned checkpoints to produce high-quality visual outputs in various styles and formats.

Purpose

This action addresses the need for personalized image generation by allowing developers to input a face image and receive a uniquely generated image based on that reference. It's particularly useful for creating avatars, character designs, or any scenario where a specific facial reference is required.

Input Requirements

The input for this action must be structured as a JSON object that includes the following required fields:

  • faceImage: A URI pointing to the face image used for generation.
  • Additional optional fields include:
    • prompt: A text description to guide the image generation.
    • width and height: Dimensions of the output image.
    • facialStyle: The visual style of the generated face (high-fidelity or stylized).
    • outputFormat: The desired format of the output image (webp, jpg, png).
    • outputQuality: A numeric value from 0 to 100 indicating the quality of the image.
    • modelSelection: Choice of the model for image generation.
    • negativePrompt: Elements to exclude from the generated image.
    • numberOfImages: The number of images to generate (1 to 10).

Expected Output

The expected output is a URI pointing to the generated image, which can be directly used in applications or shared across platforms.

Use Cases for this Action

  • Game Development: Create unique character designs based on player-uploaded photos.
  • Social Media: Generate custom avatars or profile pictures that reflect user preferences.
  • Marketing: Design personalized promotional materials featuring custom visuals.
  • Art and Creativity: Enable artists to visualize concepts based on real-life references.

```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 = "7938ce6c-9f76-4843-bac9-a77cb907868b" # Action ID for: Generate Image from Face

# 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": "anime middle aged professional guy",
  "faceImage": "https://replicate.delivery/pbxt/KtD7T0zAQ4YU1vI4CptsLMSVzL239UWFHRcZ1DgWAhyVsfuh/guy.webp",
  "facialStyle": "high-fidelity",
  "outputFormat": "webp",
  "outputQuality": 80,
  "modelSelection": "animated - starlightXLAnimated_v3",
  "negativePrompt": "boy",
  "numberOfImages": 1
}

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
Pulid Base's "Generate Image from Face" action offers developers a robust and flexible solution for creating personalized images that enhance user engagement and creativity. By streamlining the image generation process, it opens up new possibilities across various industries, from gaming to marketing. To harness the full potential of Pulid Base, start integrating this action into your projects today and explore the creative opportunities that await!
← Back to All Articles