image-to-video

minimax/video-01

Hailuo Video-01 boasts high compression rates, excellent text responsiveness, and diverse styles, while supporting native high resolution and high frame rate videos, comparable to cinematic quality.

Doc

Hint: You can drag and drop a file or click to upload

The model automatically optimizes incoming prompts to improve build quality.

Idle

Your request will cost $0.5 per run.

For $10 you can run this model approximately 20 times.

One more thing:

ExamplesView all

README

Hailuo Video-01

video-01 is MiniMax's first officially released AI-native video generation model. It is designed to produce visually compelling, high-definition short videos from either text prompts or image inputs.

Key Features

  • 720p Resolution at 25fps
    Generates high-definition videos with smooth motion and cinematic quality.

  • Cinematic Camera Movements
    Built-in camera effects create dynamic and engaging storytelling visuals.

  • Text-to-Video & Image-to-Video Modes
    Supports both pure text input and hybrid text + image input workflows.

  • High Text Responsiveness
    Understands and reflects nuanced text prompts accurately in the visual output.

  • High Compression Efficiency
    Optimized for fast rendering and lower resource consumption without compromising quality.

  • Diverse Visual Styles
    Adapts to a wide range of aesthetics, from realistic to stylized video generations.

  • Native High Resolution and Frame Rate
    Capable of producing content that approaches cinematic standards in visual fidelity.

Current Limitations

  • Video Duration: Up to 6 seconds.
    (Upcoming versions will expand support to 10-second videos.)