Vidu Template

vidu-template

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~100 sec

StatusActive

Version

0.0.1

Updated8 days ago

Live Demo

Average runtime: ~100 seconds

Input

Configure model parameters

Image Url

File upload is currently disabled

Output

View generated results

Result

Preview, share or download your results with a single click.

Each execution costs $0.35 With $1 you can run this model about 2 times.

API Reference

View Full Documentation

Prerequisites

Create an API Key from the Eachlabs Console
Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time

API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}

def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "vidu-template",
            "version": "0.0.1",
            "input": {
  "seed": 0,
  "image_url": "your image url here",
  "template_name": "minecraft"
},
            "webhook_url": ""
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

The API uses a two-step process: create prediction and poll for results
Response time: ~100 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

Vidu Template is a video generation model that transforms static images into dynamic videos by applying a variety of predefined motion templates. By leveraging advanced diffusion techniques, it enables users to create engaging visual content without requiring extensive video editing skills.

Technical Specifications

Image Quality: Use high-resolution images with clear subjects to ensure optimal video output.

Template Selection: Choose templates that align with the content and mood of your image for coherent results.

Seed Consistency: Setting a specific seed value allows for reproducible results, which is useful for iterative design processes.

Key Considerations

Template Limitations: Some templates may require specific image compositions or multiple images to function correctly.

Content Appropriateness: Ensure that the selected template matches the context and subject of the image to avoid incongruent results.

Legal Information for Vidu Template

By using this Vidu Template, you agree to:

Vidu Terms Of Use

Vidu Privacy Policy

Tips & Tricks

Image URL: Provide a direct URL to a high-quality image. Ensure the image is well-lit and the subject is clearly visible.

Seed: Use a fixed integer value to reproduce specific results. For varied outputs, allow the seed to be randomly assigned.

Template Name: Select from the available templates that best suit your image's theme. For example:

hugging for affectionate scenes
ghibli for a whimsical, animated style
fashion_stride for runway or fashion-related images.

Experiment with different templates to discover the most fitting effect for your image.

Capabilities

Image-to-Video Transformation: Convert static images into dynamic videos using a variety of motion templates

Template Diversity: Access a broad selection of templates to apply different styles and effects to your images.

What can I use for?

Social Media Content: Create engaging videos for platforms like Instagram, TikTok, or Facebook.

Marketing Materials: Develop dynamic visuals for promotional campaigns or advertisements.

Personal Projects: Transform personal photos into animated keepsakes or digital art pieces.

Storytelling: Enhance narratives by adding motion to illustrative images or storyboards.

Things to be aware of

Template Exploration: Test various templates with the same image to observe different stylistic outcomes

Seed Variation: Adjust the seed value to generate diverse versions of the same template effect.

Image Pairing: Combine multiple images in templates that support multi-image inputs to create more complex animations.

Limitations

Template Dependency: The quality of the output is heavily reliant on the chosen template and its compatibility with the input image.

Static Input: Currently, Vidu Template only supports static images as input; it does not process video or animated inputs.

Output Format: MP4

Related AI Models