---
title: Vidu 2.0 | Runware Docs
url: https://runware.ai/docs/models/vidu-2-0
description: Fast 1080p AI video generation with strong consistency
---
# Vidu 2.0

![Vidu 2.0](https://assets.runware.ai/covers/vidu-2-0.jpg)

Vidu 2.0 is a generative video model for rapid 1080p clip creation. It targets 4 second and 8 second shots with strong subject consistency and support for batch workflows. Developers can drive cinematic clips from text prompts and templates with improved speed and lower cost.

- **Status**: live
- **ID**: `vidu:2@0`
- Try in Playground
- **Creator**: Vidu
- **Release Date**: January 15, 2025
- **Capabilities**: Image to Video, Checkpoint

## Pricing

$0.11 from, per run · ~1m 1s per request

**Rates** (per run)

- 720p · 4s: `$0.11`
- 720p · 8s: `$0.275`

**3 example generations**

- [reference-to-video](https://runware.ai/docs/models/vidu-2-0/examples#example-adaptive-handcycle-social-video-ad) · 720p · 4s: `$0.22` (~1m 1s)
- [first-last-frame](https://runware.ai/docs/models/vidu-2-0/examples#example-industrial-wool-mill-music-video) · 720p · 8s: `$0.275` (~2m 8s)
- [first-frame](https://runware.ai/docs/models/vidu-2-0/examples#example-ocean-sensor-network-logo-loop) · 1080p · 4s: `$0.275` (~37s)

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`.

---

Provide exactly one of: `inputs.frameImages`, `inputs.referenceImages`.

---

When `duration` is `8`, `width` must be `1280` and `height` must be `720`.

---

When `inputs.referenceImages` is provided, `duration` must be `4` and dimensions are limited to `1280×720` or `640×360`.

---

When `providerSettings.vidu.bgm` is provided, `duration` must be `4`.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1080p (1:1)` | `1080x1080` |
| `720p (16:9)` | `1280x720` |
| `360p (16:9)` | `640x360` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/vidu-2-0#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/vidu-2-0#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-2-0#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/vidu-2-0#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-2-0#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-2-0#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-2-0#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-2-0#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-2-0#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/vidu-2-0#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-2-0#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-2-0#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-2-0#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/vidu-2-0#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.

### [referenceImages](https://runware.ai/docs/models/vidu-2-0#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/vidu-2-0#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-2-0#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-2-0#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-2-0#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `vidu:2@0`

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-2-0#request-positiveprompt)

- **Type**: `string`
- **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-2-0#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided or inputs.referenceImages is provided or duration is 8
- **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-2-0#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided or inputs.referenceImages is provided or duration is 8
- **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)

### [duration](https://runware.ai/docs/models/vidu-2-0#request-duration)

- **Type**: `integer`
- **Default**: `4`

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).

**Allowed values**: `4` `8`

### [seed](https://runware.ai/docs/models/vidu-2-0#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.

### [bgm](https://runware.ai/docs/models/vidu-2-0#request-providersettings-vidu-bgm)

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

Enable background music generation.

### [movementAmplitude](https://runware.ai/docs/models/vidu-2-0#request-providersettings-vidu-movementamplitude)

- **Path**: `providerSettings.vidu.movementAmplitude`
- **Type**: `string`
- **Default**: `auto`

Movement intensity in the generated video.

**Allowed values**:

- `auto` Automatically determines movement level based on content.
- `small` Minimal movement with subtle animations.
- `medium` Moderate movement with balanced dynamics.
- `large` High movement with pronounced animations.

## Response Parameters

### [taskType](https://runware.ai/docs/models/vidu-2-0#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-2-0#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-2-0#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/vidu-2-0#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/vidu-2-0#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/vidu-2-0#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/vidu-2-0#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-2-0#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/vidu-2-0#response-cost)

- **Type**: `float`

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

## Examples

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/vidu-2-0/ad9e84d6-872a-4f70-bcbc-1731eff38ba8.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "aaa5fd58-a306-49dd-aa5c-be7961ffd158",
  "model": "vidu:2@0",
  "positivePrompt": "Continue directly from the supplied first frame as a polished four-second motion-identity loop for an oceanographic sensor network. Preserve the exact PELAGIC ARRAY lettering, centered composition, logo geometry, colors, and midnight-navy background. The coral data point emits a thin phosphor-mint sonar ring that expands smoothly across the open square; as it passes through the three logo arcs, each arc illuminates in sequence with a restrained bioluminescent glow. Tiny precise data particles briefly trace circular current paths around the symbol, then stream back into the central point. Add subtle underwater light falloff and elegant technical depth while keeping the design graphic, minimal, and highly legible. The glow settles, particles disappear, and the ring contracts cleanly so the final moment visually returns to the unchanged opening logo for a seamless loop. Locked camera, no cuts, no extra words, no warped typography, no new symbols, no photoreal ocean imagery.",
  "width": 1080,
  "height": 1080,
  "duration": 4,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/ae9e4e5e-9659-43c4-b16c-94b11b1cd223.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/vidu-2-0/976200c3-9d24-48ce-8e61-983a155f79b6.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a1331238-2537-4bbf-a466-8bfde429793c",
  "model": "vidu:2@0",
  "positivePrompt": "Create one uninterrupted eight-second performance shot using the supplied images as the exact first and last visual endpoints. Begin in the symmetrical wide composition: the vocalist is perfectly still, facing camera with her cream baritone guitar lowered while the old wool mill is quiet. The camera begins a smooth, deliberate dolly forward. She lifts the guitar, plants her boots and starts an intense, rhythmically precise performance while maintaining direct eye contact. In a plausible mechanical progression, the carding drums behind her engage, belts begin turning and the long ivory wool ribbons start traveling through the machines. Their motion sends fine loose fibers drifting into the warm window backlight. Her burnt-orange suit catches brief amber highlights as she moves, while the oxidized teal machinery and mill architecture remain stable. Build energy continuously without a cut, arriving naturally at the supplied closer final composition with the performer playing and illuminated fibers streaming around her. Preserve her face, close-cropped hair, wardrobe, guitar design and the mill layout throughout. Grounded practical music-video cinematography, restrained choreography, subtle handheld texture layered over the forward dolly, analog 16mm grain, tactile industrial realism. No scene change, morphing, additional people, lettering or logos.",
  "width": 1280,
  "height": 720,
  "duration": 8,
  "providerSettings": {
    "vidu": {
      "movementAmplitude": "small"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/11d3fac4-e6e7-4c50-9c9c-faa5aa3deed9.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/c810c1fc-4793-44c9-86cd-b0fd6207fdeb.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/vidu-2-0/9447ce36-1e05-43d6-94b4-9f875216aaf5.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "99a2596d-d7a4-4ede-a266-bc1a1efc6d04",
  "model": "vidu:2@0",
  "positivePrompt": "Create a polished 4-second landscape social media video ad for an adaptive outdoor mobility company. Preserve the reference handcycle's matte cobalt triangular frame, orange wheel rims, three chunky tires, black bucket seat, and hand-crank construction. Show an athletic adult rider wearing a saffron windbreaker and matte white helmet powering the handcycle along a hard-packed desert trail. One continuous low tracking shot races beside the front wheel, then eases wider as the rider sweeps through a bend; the cranks turn naturally, wheels spin rapidly, suspension reacts to the terrain, and a controlled ribbon of pale dust catches the light. Vast chalk-white rock formations and clear turquoise sky create a bold modern sports-campaign palette. Crisp late-afternoon sunlight, sculpted shadows, realistic anatomy and mechanics, premium commercial cinematography, exhilarating but credible motion, subject sharp against subtle background motion blur. Keep the complete handcycle readable in the wide composition with clean negative space. No text, logos, interface, borders, or end card.",
  "width": 1280,
  "height": 720,
  "duration": 4,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/db104789-0377-4b69-a059-4b5abaf72b57.jpg"
    ]
  }
}
```