> ## Documentation Index
> Fetch the complete documentation index at: https://docs.varg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedance 2

> ByteDance's flagship video generation model — excellent quality with text-to-video, image-to-video, video editing, and video extension

## Overview

Seedance 2 is ByteDance's latest video generation model, available through varg via PiAPI. It produces high-fidelity videos with strong motion coherence and prompt adherence. Two variants are available:

| Model ID                  | Quality | Speed   | Credits | \~Cost |
| ------------------------- | ------- | ------- | ------- | ------ |
| `seedance-2-preview`      | Best    | \~4 min | 250     | \$2.50 |
| `seedance-2-fast-preview` | Good    | \~3 min | 150     | \$1.50 |

## Quick start

<CodeGroup>
  ```typescript SDK theme={null}
  import { createVarg } from "vargai/ai"

  const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

  const result = await varg.videoModel("seedance-2-preview").generate({
    prompt: "a golden retriever running through autumn leaves in slow motion",
    duration: 5,
    aspectRatio: "16:9",
  })

  console.log(result.video.url)
  ```

  ```bash cURL theme={null}
  # Submit generation
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "seedance-2-preview",
      "prompt": "a golden retriever running through autumn leaves in slow motion",
      "duration": 5,
      "aspect_ratio": "16:9"
    }'

  # Poll for result (use job_id from response)
  curl https://api.varg.ai/v1/jobs/JOB_ID \
    -H "Authorization: Bearer $VARG_API_KEY"
  ```
</CodeGroup>

## Capabilities

Seedance 2 supports four generation modes:

### Text-to-video

Generate video from a text prompt alone.

<CodeGroup>
  ```typescript SDK theme={null}
  const result = await varg.videoModel("seedance-2-preview").generate({
    prompt: "aerial shot of a futuristic city at sunset, flying cars, neon lights",
    duration: 10,
    aspectRatio: "16:9",
  })
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "seedance-2-preview",
      "prompt": "aerial shot of a futuristic city at sunset, flying cars, neon lights",
      "duration": 10,
      "aspect_ratio": "16:9"
    }'
  ```
</CodeGroup>

### Image-to-video

Animate a still image. Supports up to 9 reference images — use `@image1`, `@image2`, etc. in your prompt to reference them.

<CodeGroup>
  ```typescript SDK theme={null}
  const result = await varg.videoModel("seedance-2-preview").generate({
    prompt: "@image1 the woman turns to face the camera and smiles",
    imageUrls: ["https://example.com/portrait.jpg"],
    duration: 5,
  })
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "seedance-2-preview",
      "prompt": "@image1 the woman turns to face the camera and smiles",
      "duration": 5,
      "files": [{ "url": "https://example.com/portrait.jpg" }]
    }'
  ```
</CodeGroup>

### Video editing

Edit an existing video based on a text prompt. When a video URL is provided, the `duration` parameter is ignored.

<CodeGroup>
  ```typescript SDK theme={null}
  const result = await varg.videoModel("seedance-2-preview").generate({
    prompt: "change the background to a tropical beach",
    videoUrls: ["https://example.com/original.mp4"],
  })
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "seedance-2-preview",
      "prompt": "change the background to a tropical beach",
      "files": [{ "url": "https://example.com/original.mp4" }]
    }'
  ```
</CodeGroup>

### Video extension

Extend a previously generated video by providing its task ID.

```typescript SDK theme={null}
const result = await varg.videoModel("seedance-2-preview").generate({
  prompt: "the camera continues to pull back revealing the full landscape",
  parentTaskId: "previous-task-id",
  duration: 5,
})
```

## Parameters

<ResponseField name="prompt" type="string" required>
  Text description of the video to generate. For image-to-video, reference images with `@image1`, `@image2`, etc.
</ResponseField>

<ResponseField name="duration" type="5 | 10 | 15" default="5">
  Video duration in seconds. Only 5, 10, or 15 are accepted — any other value will cause an error. Ignored in video edit mode.
</ResponseField>

<ResponseField name="aspect_ratio" type="string" default="16:9">
  Output aspect ratio. Supported values: `16:9`, `9:16`, `4:3`, `3:4`.
</ResponseField>

<ResponseField name="files" type="array">
  Array of `{ url: string }` objects. Images trigger image-to-video mode. A video file (`.mp4`, `.webm`, `.mov`) triggers video edit mode. Maximum 9 images.
</ResponseField>

<ResponseField name="provider_options" type="object">
  Pass-through options for the PiAPI provider. Rarely needed.
</ResponseField>

<Warning>
  **Duration must be exactly 5, 10, or 15 seconds.** Values like 3, 7, or 12 will fail. This is a hard constraint from the Seedance model.
</Warning>

## Pricing

| Model                     | Credits | USD    |
| ------------------------- | ------- | ------ |
| `seedance-2-preview`      | 250     | \$2.50 |
| `seedance-2-fast-preview` | 150     | \$1.50 |

Pricing is flat per generation regardless of duration.

## Tips

* **Image-to-video produces better results** than text-to-video. Generate a reference image first with `nano-banana-pro`, then animate it.
* **Use `@imageN` syntax** to reference specific images in multi-image prompts. This gives you control over which image maps to which element.
* **Be specific about motion** — describe camera movements ("slow pan left", "zoom in") and subject actions ("walks toward camera", "turns around") explicitly.
* **Fast preview** is a good starting point for iteration. Switch to the full preview model for final renders.
* **Aspect ratios matter** — `9:16` for TikTok/Reels/Shorts, `16:9` for YouTube/landscape, `4:3` for social posts.

## Composition example

Use Seedance in a full video composition with the SDK:

```tsx theme={null}
/** @jsxImportSource vargai */
import { Render, Clip, Image, Video, Speech, Captions } from "vargai"
import { createVarg } from "vargai/ai"

const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

const scene = Image({
  model: varg.imageModel("nano-banana-pro"),
  prompt: "professional woman in modern office, confident pose",
  aspectRatio: "9:16",
})

export default (
  <Render width={1080} height={1920} fps={30}>
    <Clip duration={5}>
      <Video
        model={varg.videoModel("seedance-2-preview")}
        prompt={{ text: "@image1 she turns and smiles at the camera", images: [scene] }}
        duration={5}
      />
    </Clip>
  </Render>
)
```

## Related models

<CardGroup cols={2}>
  <Card title="Kling V3" icon="film" href="/models/video/kling-v3">
    Best overall video model. Supports 3-15s flexible duration.
  </Card>

  <Card title="Sora 2" icon="video" href="/models/video/sora-2">
    OpenAI's video model. Good for cinematic shots.
  </Card>

  <Card title="Wan 2.5" icon="wand-magic-sparkles" href="/models/video/wan-2">
    Budget-friendly video generation with good character motion.
  </Card>

  <Card title="Nano Banana Pro" icon="image" href="/models/image/nano-banana">
    Generate reference images to use with Seedance image-to-video.
  </Card>
</CardGroup>