Hailuo Video

hailuo-video

Create professional, high-quality videos with advanced AI Hailuo (Minimax) Video

Partner Model

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~424 sec

StatusActive

Version

0.0.1

Updated1 day ago

Live Demo

Average runtime: ~424 seconds

Input

Configure model parameters

Prompt

Enter your prompt to generate video

let this person slowly hug the person on the left

First Frame Image

Enter first frame for the video (OPTIONAL)

File upload is currently disabled

PNGJPEGJPG

Output

View generated results

Result

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

Each execution costs $0.43 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": "hailuo-video",
            "version": "0.0.1",
            "input": {
  "prompt_optimizer": false,
  "first_frame_image": "your_file.png",
  "prompt": "your prompt here"
}
        }
    )
    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: ~424 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

Video-01 (also known as Hailuo) is MiniMax's AI video generation model that can create 6-second videos from text descriptions or images.

Technical Specifications

720p video resolution output

25fps frame rate

High compression ratios

High text prompt compliance

Various style options available

The model accepts image files in JPG and PNG formats as input

The minimum pixel on the short side of the image: should be 300px

Key Considerations

Complex Prompts:
Licensing:
- Ensure proper attribution and check terms for commercial usage.

Privacy Policy

When using Hailuo AI model, data is sent from Eachlabs to MiniMax. For more information:

Tips & Tricks

Optimize Text Descriptions:
- Use sensory details to enhance outcomes. Example: "A foggy forest with soft sunlight filtering through the trees."
Combine Inputs:
- Pair a text prompt with an image for specific results. Example: Provide an image of a car and add a prompt like "Driving through a desert at sunset."
Experiment with Styles:
- Try different keywords such as “cinematic,” “sketch,” “hyperrealistic,” or “vintage film.”

Capabilities

AI-Driven Video Creation: Hailuo AI Generate high-quality videos from scratch using text, images, or clips.

Real-Time Enhancement: Add effects, adjust colors, or modify scenes in real-time.

Multi-Style Outputs: Produce videos with styles ranging from cinematic to abstract art.

Resolution Flexibility: Create videos in various resolutions to suit diverse platforms and purposes.

What can I use for?

Marketing and Advertising: Create eye-catching ads or promotional videos.

Social Media Content: Hailuo AI generates short, engaging clips for Instagram, TikTok, or YouTube.

Creative Storytelling: Develop visuals for animations or short films.

Educational Materials: Produce instructional videos with dynamic visuals.

Product Demonstrations: Showcase products in a 360-degree view or with visual effects.

Things to be aware of

Nature Scenes:

Text Prompt: "A serene beach with turquoise waters and palm trees swaying in the breeze."

Image-to-Video:

Input an image of a cityscape with the prompt: "Transform into a time-lapse of city lights turning on at dusk."

Cinematic Effects:

Prompt: "A slow-motion scene of leaves falling in a forest during autumn."

Multi-Scene Videos:

Example: "Scene 1: A snowy mountain. Scene 2: A cabin with a warm fireplace."

Artistic Styles:

Experiment with styles like “oil painting,” “watercolor,” or “neon lights.”

Dynamic Movements:

Use prompts like "Smooth camera pan across a desert at sunset."
Generate a short video clip from a detailed text description
Convert a still image into a dynamic video with camera motion
Test different text prompts to understand style variations
Create videos with varying conditivarying conditions of lighting and atmospheres
Experiment with various scene descriptions
Try generating videos with different moods and emotions
Test the model's ability to handle different types of motion
Create videos with different camera movement styles
Generate videos for different use cases (product showcase, nature scenes)
Compare results between simple and complex prompts

Limitations

Abstract Prompts: Complex or abstract prompts may not translate well into coherent videos.

Currently limited to 6-second video generation

10-second video support planned for future release

Output Format: MP4

Related AI Models