跳到正文
Vercel Blog(vercel.com)· Zachary Chen·· 7 天前品質評分58

Vercel AI Gateway 開放使用 Seedance 2.5 Flash 生成影片

Seedance 2.5 Flash now available on AI Gateway

重點導讀

想用文字或現有素材生成影片時,Seedance 2.5 Flash 現在可透過 Vercel AI Gateway 使用。

  • 它是 Seedance 2.5 的較快、較低成本版本,可生成帶同步音訊的影片,也能參考圖片、影片或音訊,或編輯和延長既有影片。
  • 影片長度為 4 到 30 秒,最高 720p、每秒 24 格,並支援橫向、方形和直向畫面。
  • 使用者可透過 AI SDK 7 呼叫這個模型。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

正文

# Seedance 2.5 Flash now available on AI Gateway - Vercel
Skip to content

[](https://vercel.com/home)

Copy Wordmark Copy Logo

Download Brand Assets Brand Guidelines

Products

Agent Stack

Core Platform

Tools

Resources

Learn

Build

Explore

EnterprisePricing

Get a DemoLog InSign Up

Ask AIDashboard

Image 1

  • * *

Products

Agent Stack

Core Platform

Tools

Resources

Learn

Build

Explore

Enterprise

Pricing

Get a Demo

Log InSign Up

Seedance 2.5 Flash now available on AI Gateway

Image 2Image 3

Zachary Chen, Jerilyn Zheng

BlogChangelog

16 Nov 2026

1 min read

Copy

ByteDance’s Seedance 2.5 Flash is now available on AI Gateway.

Seedance 2.5 Flash is a faster, lower-cost version of Seedance 2.5. The output is close to the standard model in human realism, reference-based editing, and prompt adherence.

Generate videos with synchronized audio from text prompts or image, video, and audio references. Clips can be 4 to 30 seconds long at up to 720p and 24 frames per second, in landscape, square, or portrait formats. You can also edit or extend existing videos, or provide images to set the first and last frames.

Use bytedance/seedance-2.5-flash with AI SDK 7 to generate a video with audio from a text prompt:

AI SDK

AI SDK AI SDK AI CLI AI CLI

1import { experimental_generateVideo as generateVideo } from 'ai';2
3const { videos } = await generateVideo({4  model: 'bytedance/seedance-2.5-flash',5  prompt: 'A paper boat drifts down a rain-soaked city street at dusk.',6  aspectRatio: '16:9',7  duration: 5,8});

Copy for agentView model details ↗

To guide generation with reference images and videos, pass their URLs in inputReferences. Images and videos are numbered separately in the prompt as [Image 1], [Video 1], and so on:

AI SDK

AI SDK AI SDK

1import { experimental_generateVideo as generateVideo } from 'ai';2
3const { videos } = await generateVideo({4  model: 'bytedance/seedance-2.5-flash',5  prompt: 'The lion from [Image 1] walks through a sunlit meadow, filmed like [Video 1].',6  aspectRatio: '16:9',7  duration: 5,8  inputReferences: [9    {10      data: '...',11      mediaType: 'image/jpeg',12    },13    {14      data: '...',15      mediaType: 'video/mp4',16    },17  ],18});

Copy for agentView model details ↗

Try Seedance 2.5 Flash in the model playground, or follow the video generation quickstart.

Agent Stack

Core Platform

Security

Tools

Frameworks

SDKs

Build

Learn

Explore

Company

Legal & Trust

Social

  • Image 4: VercelImage 5: Vercel

Loading status…

Select a display theme:system light dark

來源: Vercel Blog (vercel.com)
開啟原文

讀者討論

理性交流 · 即時討論