ByteDance Provider

The ByteDance provider contains support for the Seedance family of video generation models through the BytePlus ModelArk platform. Seedance provides high-quality text-to-video and image-to-video generation capabilities, including audio-video synchronization, first-and-last frame control, and multi-reference image generation.

Setup

The ByteDance provider is available via the @ai-sdk/bytedance module. You can install it with

pnpm add @ai-sdk/bytedance

Provider Instance

You can import the default provider instance byteDance from @ai-sdk/bytedance:

1
import { byteDance } from '@ai-sdk/bytedance';

If you need a customized setup, you can import createByteDance and create a provider instance with your settings:

1
import { createByteDance } from '@ai-sdk/bytedance';
2

3
const byteDance = createByteDance({
4
  apiKey: 'your-api-key', // optional, defaults to ARK_API_KEY environment variable
5
  baseURL: 'custom-url', // optional
6
  headers: {
7
    /* custom headers */
8
  }, // optional
9
});

You can use the following optional settings to customize the ByteDance provider instance:

• baseURL string

  Use a different URL prefix for API calls, e.g. to use proxy servers. The default prefix is https://ark.ap-southeast.bytepluses.com/api/v3.

• apiKey string

  API key that is being sent using the Authorization header. It defaults to the ARK_API_KEY environment variable. You can obtain an API key from the BytePlus console.

• headers Record<string,string>

  Custom headers to include in the requests.

• fetch (input: RequestInfo, init?: RequestInit) => Promise<Response>

  Custom fetch implementation. You can use it as a middleware to intercept requests, or to provide a custom fetch implementation for e.g. testing.

Video Models

You can create ByteDance video models using the .video() factory method. For more on video generation with the AI SDK see generateVideo().

Text-to-Video

Generate videos from text prompts:

1
import {
2
  byteDance,
3
  type ByteDanceVideoProviderOptions,
4
} from '@ai-sdk/bytedance';
5
import { experimental_generateVideo as generateVideo } from 'ai';
6

7
const { video } = await generateVideo({
8
  model: byteDance.video('seedance-1-0-pro-250528'),
9
  prompt:
10
    'Photorealistic style: Under a clear blue sky, a vast expanse of white daisy fields stretches out. The camera gradually zooms in and fixates on a close-up of a single daisy.',
11
  aspectRatio: '16:9',
12
  duration: 5,
13
  providerOptions: {
14
    bytedance: {
15
      watermark: false,
16
    } satisfies ByteDanceVideoProviderOptions,
17
  },
18
});
19

20
console.log(video.url);

Image-to-Video

Generate videos from a first-frame image with an optional text prompt:

1
import {
2
  byteDance,
3
  type ByteDanceVideoProviderOptions,
4
} from '@ai-sdk/bytedance';
5
import { experimental_generateVideo as generateVideo } from 'ai';
6

7
const { video } = await generateVideo({
8
  model: byteDance.video('seedance-1-5-pro-251215'),
9
  prompt: {
10
    image: 'https://example.com/first-frame.png',
11
    text: 'The cat slowly turns its head and blinks',
12
  },
13
  duration: 5,
14
  providerOptions: {
15
    bytedance: {
16
      watermark: false,
17
    } satisfies ByteDanceVideoProviderOptions,
18
  },
19
});

Image-to-Video with Audio

Seedance 1.5 Pro supports generating synchronized audio alongside the video:

1
import {
2
  byteDance,
3
  type ByteDanceVideoProviderOptions,
4
} from '@ai-sdk/bytedance';
5
import { experimental_generateVideo as generateVideo } from 'ai';
6

7
const { video } = await generateVideo({
8
  model: byteDance.video('seedance-1-5-pro-251215'),
9
  prompt: {
10
    image: 'https://example.com/pianist.png',
11
    text: 'A young man sits at a piano, playing calmly. Gentle piano music plays in sync with his movements.',
12
  },
13
  duration: 5,
14
  providerOptions: {
15
    bytedance: {
16
      generateAudio: true,
17
      watermark: false,
18
    } satisfies ByteDanceVideoProviderOptions,
19
  },
20
});

First-and-Last Frame Video

Generate smooth transitions between a starting and ending keyframe image:

1
import {
2
  byteDance,
3
  type ByteDanceVideoProviderOptions,
4
} from '@ai-sdk/bytedance';
5
import { experimental_generateVideo as generateVideo } from 'ai';
6

7
const { video } = await generateVideo({
8
  model: byteDance.video('seedance-1-5-pro-251215'),
9
  prompt: {
10
    image: 'https://example.com/first-frame.jpg',
11
    text: 'Create a 360-degree orbiting camera shot based on this photo',
12
  },
13
  duration: 5,
14
  providerOptions: {
15
    bytedance: {
16
      lastFrameImage: 'https://example.com/last-frame.jpg',
17
      generateAudio: true,
18
      watermark: false,
19
    } satisfies ByteDanceVideoProviderOptions,
20
  },
21
});

Multi-Reference Image-to-Video

Using the Seedance 1.0 Lite I2V model, you can provide multiple reference images (1-4) that the model uses to faithfully reproduce object shapes, colors, and textures:

1
import {
2
  byteDance,
3
  type ByteDanceVideoProviderOptions,
4
} from '@ai-sdk/bytedance';
5
import { experimental_generateVideo as generateVideo } from 'ai';
6

7
const { video } = await generateVideo({
8
  model: byteDance.video('seedance-1-0-lite-i2v-250428'),
9
  prompt:
10
    'A boy wearing glasses and a blue T-shirt from [Image 1] and a corgi dog from [Image 2], sitting on the lawn from [Image 3], in 3D cartoon style',
11
  aspectRatio: '16:9',
12
  duration: 5,
13
  providerOptions: {
14
    bytedance: {
15
      referenceImages: [
16
        'https://example.com/boy.png',
17
        'https://example.com/corgi.png',
18
        'https://example.com/lawn.png',
19
      ],
20
      watermark: false,
21
    } satisfies ByteDanceVideoProviderOptions,
22
  },
23
});

Video Provider Options

The following provider options are available via providerOptions.bytedance:

Generation Options

• watermark boolean

  Whether to add a watermark to the generated video.

• generateAudio boolean

  Whether to generate synchronized audio for the video. Only supported by Seedance 1.5 Pro.

• cameraFixed boolean

  Whether to fix the camera during generation.

• returnLastFrame boolean

  Whether to return the last frame of the generated video. Useful for chaining consecutive videos.

• serviceTier 'default' | 'flex'

  Inference tier. 'default' for online inference. 'flex' for offline inference at 50% of the price, with higher latency (response times on the order of hours).

• draft boolean

  Enable draft sample mode for low-cost preview generation. Only supported by Seedance 1.5 Pro. Generates a 480p preview video for rapid iteration before committing to a full-quality generation.

Image Input Options

• lastFrameImage string

  URL of the last frame image for first-and-last frame video generation. The model generates smooth transitions between the first frame (provided via the image prompt) and this last frame. Supported by Seedance 1.5 Pro, 1.0 Pro, and 1.0 Lite I2V.

• referenceImages string[]

  Array of reference image URLs (1-4 images) for multi-reference image-to-video generation. The model extracts key features from each image and reproduces them in the video. Use [Image 1], [Image 2], etc. in your prompt to reference specific images. Supported by Seedance 1.0 Lite I2V.

Polling Options

• pollIntervalMs number

  Control how frequently the API is checked for completed videos while they are being processed. Defaults to 3000ms.

• pollTimeoutMs number

  Maximum time to wait for video generation to complete before timing out. Defaults to 300000ms (5 minutes).

Video Model Capabilities

Supported aspect ratios: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive (image-to-video only).

All models output MP4 video at 24 fps.