# PixVerse V6 Max Image To Video

> Generate videos from images with PixVerse V6 Max, with optional audio and multi-clip generation.


## Overview

- **Endpoint**: `https://fal.run/pixverse/v6/max/image-to-video`
- **Model ID**: `pixverse/v6/max/image-to-video`
- **Category**: image-to-video
- **Kind**: inference
**Tags**: image-to-video



## Pricing

Billing is calculated per second of video generated. For **360p**, your request will cost **$0.054** per second without audio and **$0.081** with audio; for **540p**, **$0.081** without audio and **$0.099** with audio; for **720p**, **$0.099** without audio and **$0.135** with audio; and for **1080p**, **$0.198** without audio and **$0.252** with audio. Multi-clip generation has no additional surcharge. An **8-second 1080p** video with audio costs **$2.016**.

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_):
  Text prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
  - Examples: "A woman warrior with her hammer walking with his glacier wolf."

- **`resolution`** (`ResolutionEnum`, _optional_):
  The resolution of the generated video Default value: `"720p"`
  - Default: `"720p"`
  - Options: `"360p"`, `"540p"`, `"720p"`, `"1080p"`

- **`duration`** (`integer`, _optional_):
  The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds Default value: `5`
  - Default: `5`
  - Range: `1` to `15`

- **`negative_prompt`** (`string`, _optional_):
  Negative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap. Default value: `""`
  - Default: `""`
  - Examples: "blurry, low quality, low resolution, pixelated, noisy, grainy, out of focus, poorly lit, poorly exposed, poorly composed, poorly framed, poorly cropped, poorly color corrected, poorly color graded"

- **`style`** (`Enum`, _optional_):
  The style of the generated video
  - Options: `"anime"`, `"3d_animation"`, `"clay"`, `"comic"`, `"cyberpunk"`

- **`seed`** (`integer`, _optional_):
  The same seed and the same prompt given to the same version of the model
  will output the same video every time.

- **`generate_audio_switch`** (`boolean`, _optional_):
  Enable audio generation (BGM, SFX, dialogue)
  - Default: `false`

- **`generate_multi_clip_switch`** (`boolean`, _optional_):
  Enable multi-clip generation with dynamic camera changes
  - Default: `false`

- **`thinking_type`** (`Enum`, _optional_):
  Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision
  - Options: `"enabled"`, `"disabled"`, `"auto"`

- **`image_url`** (`string`, _required_):
  URL of the image to use as the first frame
  - Examples: "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png"

- **`enable_safety_checker`** (`boolean`, _optional_):
  Authorized callers may set false to request relaxed screening. Default value: `true`
  - Default: `true`



**Required Parameters Example**:

```json
{
  "prompt": "A woman warrior with her hammer walking with his glacier wolf.",
  "image_url": "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png"
}
```

**Full Example**:

```json
{
  "prompt": "A woman warrior with her hammer walking with his glacier wolf.",
  "resolution": "720p",
  "duration": 5,
  "negative_prompt": "blurry, low quality, low resolution, pixelated, noisy, grainy, out of focus, poorly lit, poorly exposed, poorly composed, poorly framed, poorly cropped, poorly color corrected, poorly color graded",
  "image_url": "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png",
  "enable_safety_checker": true
}
```


### Output Schema

The API returns the following output format:

- **`video`** (`File`, _required_):
  The generated video
  - Examples: {"url":"https://storage.googleapis.com/falserverless/model_tests/video_models/output-3.mp4","content_type":"video/mp4","file_size":6420765,"file_name":"output.mp4"}



**Example Response**:

```json
{
  "video": {
    "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/output-3.mp4",
    "content_type": "video/mp4",
    "file_size": 6420765,
    "file_name": "output.mp4"
  }
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/pixverse/v6/max/image-to-video \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A woman warrior with her hammer walking with his glacier wolf.",
     "image_url": "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png"
   }'
```

### 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(
    "pixverse/v6/max/image-to-video",
    arguments={
        "prompt": "A woman warrior with her hammer walking with his glacier wolf.",
        "image_url": "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png"
    },
    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("pixverse/v6/max/image-to-video", {
  input: {
    prompt: "A woman warrior with her hammer walking with his glacier wolf.",
    image_url: "https://v3.fal.media/files/zebra/qL93Je8ezvzQgDOEzTjKF_KhGKZTEebZcDw6T5rwQPK_output.png"
  },
  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);
```


## Deploy your own model

To run your own weights, a fine-tune or a custom pipeline on the GPUs that serve this API, deploy it on fal Serverless. GPUs from H100 (80GB) to B300 (288GB), billed per second; an H100 is $4.50/h list, as low as $2.49/h. Prices, GPU specs and deploy steps: [fal Serverless](https://fal.ai/serverless.md).

## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/pixverse/v6/max/image-to-video)
- [API Documentation](https://fal.ai/models/pixverse/v6/max/image-to-video/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=pixverse/v6/max/image-to-video)

### 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
- [Pricing](https://fal.ai/pricing.md): Model API and Serverless GPU prices
- [fal Serverless](https://fal.ai/serverless.md): Deploy your own models: GPU prices, specs and steps
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`