# H3 Max Low Poly

> Generates 768p video with audio in a retro low-poly 3D style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.


## Overview

- **Endpoint**: `https://fal.run/minimax/h3-max/styles/low-poly`
- **Model ID**: `minimax/h3-max/styles/low-poly`
- **Category**: text-to-video
- **Kind**: inference
**Tags**: low-poly, retro, 3d-animation, stylized



## Pricing

Billing is calculated per second of video generated. Video at **768p** costs **$0.08 per second**, with audio included. A **5-second** video costs **$0.40**, and a **15-second** video costs **$1.20**.

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`prompt`** (`string`, _required_):
  Describe the scene, action, camera and sound. The retro low-poly 3D style is applied automatically.
  - Examples: "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her."

- **`image_url`** (`string`, _optional_):
  Optional first-frame image. Use low-poly or retro 3D artwork for the most consistent look; the image's aspect ratio determines the output canvas.

- **`duration`** (`integer`, _optional_):
  Requested video duration in seconds. Default value: `5`
  - Default: `5`
  - Range: `5` to `15`

- **`aspect_ratio`** (`AspectRatioEnum`, _optional_):
  Video aspect ratio for text-only generation. Ignored when image_url is provided. Default value: `"16:9"`
  - Default: `"16:9"`
  - Options: `"21:9"`, `"16:9"`, `"4:3"`, `"1:1"`, `"3:4"`, `"9:16"`

- **`seed`** (`integer`, _optional_):
  Random seed. Omit to choose one automatically.



**Required Parameters Example**:

```json
{
  "prompt": "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her."
}
```

**Full Example**:

```json
{
  "prompt": "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her.",
  "duration": 5,
  "aspect_ratio": "16:9"
}
```


### Output Schema

The API returns the following output format:

- **`video`** (`File`, _required_):
  Generated 768P retro low-poly 3D video with audio.

- **`seed`** (`integer`, _required_):
  Seed used for this generation.



**Example Response**:

```json
{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/minimax/h3-max/styles/low-poly \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her."
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "minimax/h3-max/styles/low-poly",
    arguments={
        "prompt": "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("minimax/h3-max/styles/low-poly", {
  input: {
    prompt: "A woman in a red coat runs across a rainy rooftop at night, jumps over a low ventilation duct and keeps running. A helicopter searchlight sweeps the buildings behind her. The camera tracks alongside her."
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/minimax/h3-max/styles/low-poly)
- [API Documentation](https://fal.ai/models/minimax/h3-max/styles/low-poly/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=minimax/h3-max/styles/low-poly)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`