High-precision dynamic expressiveness
Even in fast-paced action or dance sequences, there is minimal distortion, depicting natural physics and smooth motion.
MiniMax's flagship video generation model. Supporting a wide range of styles from photorealistic to anime, it can generate high-quality 1080P videos with audio from text or images.
Each model has its own Playground, pricing, and field docs. Filter by capability to open the one you need.
Model id and a short note on what each capability is for.
| Model | ID | Description |
|---|---|---|
| Hailuo 2.3(text to video) | MiniMax-Hailuo-2.3-text-to-video | MiniMax’s latest top-tier video generation model, which portrays dynamic action and subtle expressions |
| Hailuo 2.3(image to video) | MiniMax-Hailuo-2.3-image-to-video | Top-tier video generation model that creates dynamic movements and delicate expressions from still images |
Equipped with advanced physics simulation and rich emotional expressiveness, it seamlessly generates videos with audio.
A moment of high-speed photography brimming with dynamism. The milky-white milk dynamically splashes out from a coconut splitting in the air, and the sunlight of the tropics shines through the water droplets. It conveys a sense of luxury and sophistication.
Prompt
A high-speed cinematic shot of a coconut splitting in the air. The white, creamy milk splashes dynamically based on fluid physics. Sunlight penetrating the water droplets, palm leaves swaying in the breeze in the backgro…
Generated with Hailuo 2.3
Generated with Hailuo H3
Generated with
On the rooftop of the futuristic city, a cyber girl passionately performs street dance in the neon rain, all captured by a dynamic camera.
Prompt
On the rooftop of the futuristic city, a cyber girl in a glowing jacket is dancing street dance. Neon rainwater reflects on the ground, with high-speed passing hover cars and giant holographic advertisements in the backg…
Generated with Hailuo 2.3
Generated with Hailuo H3
Generated with
The nostalgic JRPG style of the SFC era. Dot-art characters roam the vibrant fantasy streets of the city.
Prompt
A classic 16-bit JRPG pixel art style. A warm and bright plaza in the royal city at dusk. A party of three - a swordsman, a magician, and a priest - walk from the foreground to the background of the screen. Other NPCs (v…
Generated with Hailuo 2.3
Generated with Hailuo H3
Generated with
Typical jobs this series is used for.
Generates smooth and dynamic videos while minimizing distortion, even during intense motions such as high-speed movement, combat, and dancing.
Reproducing delicate facial expression changes and natural multi-person interactions, it supports the creation of emotionally rich short dramas.
Transform a single illustration or photo into a short video with audio, breathing life into static creatives.
With 1080P high-definition quality and commercial use support, it can be utilized for creating materials for social media ads and marketing videos.
Check production limits and starting credit cost before you pick another model for the same job.
| Model | Max clip duration (single run) | Multimodal reference inputs | Max resolution | Native audio | Sousaku starting price |
|---|---|---|---|---|---|
| Hailuo 2.3 | Up to 6 seconds | ❌ | Up to 1080P | ✅ | 4 Credits/s |
| Hailuo 2.3 Fast | Up to 6 seconds | ❌ | Up to 1080P | ❌ | 4 Credits/s |
| Hailuo H3 | Up to 15 seconds | Up to 9 assets (audio and videos) | Up to 2K | ✅ | 6 Credits/s |
From sign-up to your first successful call. The same steps work for every model.
Sign up and verify so you can issue an API key and use Playground.
Open a card above to see that model's details, pricing, and field docs.
Confirm inputs and parameters in the form before you automate.
The field docs on the detail page list required parameters. Use the same names in create_task.
Call the generate API with your key, poll until the task succeeds, then download the result.
Track credit use on the model's pricing page and in the dashboard.
Other series on Sousaku. One API key, one task flow.