---
title: Vidu Q3 | Runware Docs
url: https://runware.ai/docs/models/vidu-q3
description: Multimodal video generation with native audio and intelligent shot planning
---
# Vidu Q3

![Vidu Q3](https://assets.runware.ai/covers/vidu-q3.jpg)

Vidu Q3 is a multimodal video generation model that creates video with synchronized audio directly from text or images, supports intelligent multi-shot sequencing, and produces complete outputs with stable visuals and embedded subtitles without post-processing.

- **Status**: live
- **ID**: `vidu:4@1`
- Try in Playground
- **Creator**: Vidu
- **Release Date**: January 30, 2026
- **Capabilities**: Text to Video, Image to Video, Checkpoint, Audio

## Pricing

$0.0293 from, per second · ~1m 56s per request

**Rates** (per second)

- 540p: `$0.0293`
- 360p: `$0.0325`
- 720p: `$0.065`
- 1080p: `$0.078`

**4 example generations**

- [first-last-frame](https://runware.ai/docs/models/vidu-q3/examples#example-museum-conservation-presenter-update) · 540p · 8s: `$0.234` (~2m 1s)
- [text-to-video](https://runware.ai/docs/models/vidu-q3/examples#example-avalanche-airbag-deployment-explainer) · 720p · 5s · audio: `$0.325` (~1m 50s)
- [text-to-video](https://runware.ai/docs/models/vidu-q3/examples#example-coffee-cherry-sorter-demo) · 720p · 5s · audio: `$0.325` (~2m 35s)
- [first-frame](https://runware.ai/docs/models/vidu-q3/examples#example-mobile-farrier-service-reel) · 720p · 6s: `$0.39` (~1m 31s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.frameImages`, or specify `width/height`.

---

When `inputs.frameImages` is not provided, dimensions are limited to `640×352`, `544×400`, `480×480`, `400×544`, `352×640`, `960×528`, `816×608`, `720×720`, `608×816`, `528×960`, `1280×720`, `1104×816`, `960×960`, `816×1104`, `720×1280`, `1920×1080`, `1674×1238`, `1440×1440`, `1238×1674` or `1080×1920`.

---

When `inputs.frameImages` has at most 1 item, dimensions are limited to `640×352`, `640×360`, `544×400`, `480×480`, `360×360`, `400×544`, `352×640`, `360×640`, `960×528`, `816×608`, `720×720`, `608×816`, `528×960`, `1280×720`, `960×960`, `720×1280`, `1920×1080`, `1080×1080` or `1080×1920`.

---

When `inputs.frameImages` has 2 or more items, dimensions are limited to `960×528`, `816×608`, `720×720`, `608×816`, `528×960`, `1280×720`, `960×960`, `720×1280`, `1920×1080`, `1080×1080` or `1080×1920`.

---

When `inputs.frameImages` has 2 or more items and `resolution`, `resolution` is limited to `540p`, `720p`, `1080p`.

---

When `inputs.frameImages` is not provided, `positivePrompt` is required.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages` requires at least 1 item.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `360p (~16:9)` | `640x352` |
| `360p (16:9)` | `640x360` |
| `360p (4:3)` | `544x400` |
| `480p (1:1)` | `480x480` |
| `360p (1:1)` | `360x360` |
| `360p (3:4)` | `400x544` |
| `360p (~9:16)` | `352x640` |
| `360p (9:16)` | `360x640` |
| `540p (16:9)` | `960x528` |
| `540p (4:3)` | `816x608` |
| `540p (1:1)` | `720x720` |
| `540p (3:4)` | `608x816` |
| `540p (9:16)` | `528x960` |
| `720p (16:9)` | `1280x720` |
| `720p (4:3)` | `1104x816` |
| `720p (1:1)` | `960x960` |
| `720p (3:4)` | `816x1104` |
| `720p (9:16)` | `720x1280` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (4:3)` | `1674x1238` |
| `1440p (1:1)` | `1440x1440` |
| `1080p (1:1)` | `1080x1080` |
| `1080p (3:4)` | `1238x1674` |
| `1080p (9:16)` | `1080x1920` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/vidu-q3#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/vidu-q3#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/vidu-q3#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/vidu-q3#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/vidu-q3#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/vidu-q3#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/vidu-q3#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/vidu-q3#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/vidu-q3#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/vidu-q3#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/vidu-q3#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/vidu-q3#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/vidu-q3#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/vidu-q3#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/vidu-q3#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/vidu-q3#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/vidu-q3#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/vidu-q3#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `vidu:4@1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/vidu-q3#request-positiveprompt)

- **Type**: `string`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Min**: `2`
- **Max**: `2000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/vidu-q3#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/vidu-q3#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/vidu-q3#request-resolution)

- **Type**: `string`
- **Default**: `720p`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `360p` `540p` `720p` `1080p`

### [duration](https://runware.ai/docs/models/vidu-q3#request-duration)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `16`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

### [seed](https://runware.ai/docs/models/vidu-q3#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.vidu\` object.

### [audio](https://runware.ai/docs/models/vidu-q3#request-providersettings-vidu-audio)

- **Path**: `providerSettings.vidu.audio`
- **Type**: `boolean`

Enable audio generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/vidu-q3#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/vidu-q3#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/vidu-q3#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/vidu-q3#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/vidu-q3#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/vidu-q3#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/vidu-q3#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/vidu-q3#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/vidu-q3#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/vidu-q3/bef0d192-baf2-4201-94cf-7c481f02fd63.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "812a4d37-4daf-4906-ae4c-9db2a5574b05",
  "model": "vidu:4@1",
  "positivePrompt": "Create a concise 5-second product explainer for a professional avalanche airbag backpack, composed in cinematic 16:9 landscape. Open on a tight side view of a backcountry skier in a burnt-orange jacket pulling the red emergency handle as loose snow begins sliding around them. Instantly transition through a clean semi-transparent cutaway of the backpack: the trigger cable releases the compressed-gas cylinder, blue airflow races through the valve, and the folded airbag expands. Pull wide as the large bright-red airbag fully inflates behind the skier and keeps their upper body riding visibly near the surface of the moving powder. Finish on a crisp overhead view of the inflated airbag against white snow. Premium outdoor safety-film realism blended with precise technical visualization, icy blue-white palette with orange and red safety accents, stable product geometry, physically convincing fabric inflation and snow motion, no logos, no interface, no captions. Synchronized audio: sharp handle click, forceful compressed-gas hiss, rapid nylon unfurling, rushing powder, muffled alpine wind, then a firm inflation thump.",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "providerSettings": {
    "vidu": {
      "audio": true
    }
  }
}
```

---

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/vidu-q3/e4f74a5b-414d-42e0-9bf2-68acad90e578.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "cab55a73-c5c8-495b-83b2-9ca2379e7664",
  "model": "vidu:4@1",
  "positivePrompt": "A polished five-second product explainer for a precision optical coffee-cherry sorter, presented as cinematic photoreal industrial visualization. In one fluid macro tracking shot, glossy ripe red coffee cherries roll rapidly along a narrow matte-black conveyor inside a clean stainless-steel processing machine. The camera follows beside them as they pass beneath a bright emerald inspection light; one pale defective cherry is briefly isolated by a crisp scanning glow. At the exact moment it reaches the sorting gate, a small pneumatic nozzle fires and cleanly knocks only that cherry sideways into a reject chute while the ripe cherries continue forward into the accepted channel. Finish on the two clearly separated streams and the compact optical sensor assembly above them. Dark graphite machinery, rich crimson fruit, emerald light accents, precise controlled reflections, shallow depth of field, premium agricultural technology aesthetic, no people, no labels, no logos, no captions, no interface graphics. Synchronized environmental audio: restrained conveyor motor hum, light rhythmic cherry rattles on the belt, a brief electronic detection chirp aligned with the scan, then a sharp pneumatic hiss and soft tap as the rejected cherry lands.",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "providerSettings": {
    "vidu": {
      "audio": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/vidu-q3/23d8d921-8bb9-4c65-99d1-95732f7205e9.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "d16154a2-1765-4099-80ec-3b25ad7abc1f",
  "model": "vidu:4@1",
  "positivePrompt": "Continue directly from the supplied first frame as a polished vertical social media service reel, preserving the same female farrier, dapple-gray horse, stable, clothing, tack, dawn lighting, and natural color grade. In one continuous low-angle shot, the farrier draws the rasp smoothly across the horseshoe with confident practiced motion as fine hoof dust falls through the warm sunbeam. The horse remains relaxed, breathing gently and flicking one ear. The camera makes a subtle forward push, keeping the hoof and skilled handwork prominent while retaining the stable aisle depth. She checks the finished edge, lowers the hoof carefully, and the horse places it down with a clean, assured step toward camera. Authentic synchronized audio: rhythmic metal rasp, quiet leather creak, soft horse breath, distant stable ambience, and one crisp hoof clop. Restrained premium documentary realism, steady anatomy, physically accurate tools and hoof handling, no captions, logos, graphics, or spoken dialogue.",
  "resolution": "720p",
  "duration": 6,
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/e958e0cd-39e1-4277-916e-e6ca4706e3a4.jpg"
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/vidu-q3/dd472605-9a87-4bf2-9180-642f1460d808.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "59e6af74-817e-40aa-9376-8e7edfd853f8",
  "model": "vidu:4@1",
  "positivePrompt": "Create a polished museum conservation talking-head update in one continuous locked-camera shot, moving naturally from the supplied first frame to the supplied last frame. The conservator speaks directly to the viewer with precise, believable lip sync: “This ultraviolet scan reveals an older inventory number beneath the varnish, giving our team a vital new provenance lead.” As she speaks, she makes one restrained explanatory gesture, raises the ultraviolet torch and switches it on. Warm laboratory light gradually gives way to an indigo-violet inspection glow; subtle cyan fluorescence and the buried inventory marking emerge on the portrait panel. She briefly glances toward the discovery, then returns her eyes to camera with quiet professional satisfaction. Preserve her identity, wardrobe, anatomy, easel placement and background throughout. Natural blinking, small head movements and realistic fabric motion. Clean production dialogue with faint conservation-lab room tone, no music. Credible institutional documentary style, waist-up framing, shallow depth of field, no cuts, no camera movement, no logos, no interface elements.",
  "resolution": "540p",
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/ab0b70de-6e8b-459d-874d-5c55af64249b.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/bb75f7c4-2d81-4627-b683-7de11d2e9f48.jpg",
        "frame": "last"
      }
    ]
  }
}
```