ByteDance with Eachlabs
ByteDance's new video model, OmniHuman, is available on Eachlabs →
Eachlabs | AI Workflows for app builders

Hailuo T2V Director

hailuo-t2v-0.1

Hailuo T2V Director is an AI video model that supports a wide range of artistic styles and is designed to revolutionize how 2D illustrations come to life.

Partner Model
Fast Inference
REST API
Try in ConsoleAPI DocsExamples

Model Information

Response Time~424 sec
StatusActive
Version
0.0.1
Updated9 days ago
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-t2v-0.1",
            "version": "0.0.1",
            "input": {
  "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

Hailuo T2V Director by Minimax is an advanced AI-driven model designed to generate high-definition videos featuring cinematic camera movements. It supports 720p resolution at 25 frames per second and can produce videos up to 6 seconds in length. Users can control camera movements through specific commands within the text prompts, allowing for dynamic and engaging video content creation.

Technical Specifications

  • Video Resolution: 720p
  • Frame Rate: 25 frames per second
  • Maximum Duration: 6 seconds
  • Input Types: Text-to-video and image-to-video

Hailuo AI T2V Director utilizes advanced algorithms to interpret textual prompts and generate corresponding video sequences with specified camera movements. It supports a range of camera motions, including horizontal (e.g., [Truck left], [Pan right]), vertical (e.g., [Pedestal up], [Tilt down]), depth movements (e.g., [Push in], [Zoom out]), and special movements like [Tracking shot] and [Static shot].

Key Considerations

Prompt Specificity: Clearly describe the scene and desired camera movements to ensure accurate video generation.

Movement Placement: Position camera movement commands at logical points within the prompt to achieve the intended effect.

Combination Limit: Avoid using more than three simultaneous camera movements to maintain video coherence.


Privacy Policy

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

Tips & Tricks

Preset Shot Combinations: Utilize predefined combinations for common shots:

  • Circling Shots:
    • Left circling: [truck left, pan right, tracking shot]
    • Right circling: [truck right, pan left, tracking shot]
  • Walking Shots:
    • Left walking: [truck left, tracking shot]
    • Right walking: [truck right, tracking shot]
  • Dynamic Shots:
    • Upward tilt: [push in, pedestal up]
    • Scenic shot: [truck left, pedestal up]
    • Stage shots: [pan right, zoom in], [pan left, zoom in]
    • Downward tilt: [pedestal down, tilt up]

Sequential Movements: For complex scenes, sequence camera movements by placing commands at different points in the prompt.

Descriptive Prompts: Enhance video quality by providing detailed descriptions of the scene, lighting, and atmosphere.


Capabilities

  • Cinematic Video Generation: Produces high-definition videos with dynamic camera movements based on textual prompts.
  • Diverse Camera Controls: Supports a wide range of camera movements, including pans, tilts, zooms, and tracking shots.

  • Text and Image Inputs: Accepts both text and image inputs to generate corresponding video content.

What can I use for?

  • Content Creation: Develop engaging short videos for social media, marketing, or storytelling.
  • Educational Materials: Create illustrative videos to explain concepts or visualize scenarios.
  • Artistic Projects: Experiment with AI-generated cinematography for creative endeavors.

Things to be aware of

  • Dynamic Scenes: Describe action-packed scenarios with multiple camera movements to test Hailuo T2V Director capabilities.
  • Atmospheric Shots: Use prompts that set a specific mood or atmosphere, incorporating appropriate camera movements.

  • Subject Focus: Generate videos that focus on a particular subject, utilizing tracking shots to maintain emphasis.


Limitations

  • Video Duration: Hailuo T2V Director is limited to generating videos up to 6 seconds long.
  • Resolution Constraints: Outputs are capped at 720p resolution.
  • Complex Movements: Overly complex or rapid camera movements may not render as intended.

Output Format: MP4

Related AI Models

hailuo-video

Hailuo Video

hailuo-video

Text to Video
ltx-video

LTX-Video

ltx-video

Text to Video
ray-2-540p

Luma Ray2 540p

ray-2-540p

Text to Video
pyramid-flow

Pyramid Flow

pyramid-flow

Text to Video