WaveSpeedAI Seedance V1.5 Pro Video Generation

Generate videos using ByteDance's Seedance V1.5 Pro model via the WaveSpeed AI platform. Supports both text-to-video and image-to-video generation with 4-12 second duration at up to 1080p resolution, with optional audio generation.

Authentication

export WAVESPEED_API_KEY="your-api-key"

Get your API key at wavespeed.ai/accesskey.

Quick Start

Text-to-Video

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "bytedance/seedance-v1.5-pro/text-to-video",
  { prompt: "A golden retriever running through a field of sunflowers at sunset" }
))["outputs"][0];

Image-to-Video

The image parameter accepts an image URL. If you have a local file, upload it first with wavespeed.upload() to get a URL.

import wavespeed from 'wavespeed';

// Upload a local image to get a URL
const imageUrl = await wavespeed.upload("/path/to/photo.png");

const output_url = (await wavespeed.run(
  "bytedance/seedance-v1.5-pro/image-to-video",
  {
    image: imageUrl,
    prompt: "The person slowly turns and smiles at the camera"
  }
))["outputs"][0];

You can also pass an existing image URL directly:

const output_url = (await wavespeed.run(
  "bytedance/seedance-v1.5-pro/image-to-video",
  {
    image: "https://example.com/photo.jpg",
    prompt: "The person slowly turns and smiles at the camera"
  }
))["outputs"][0];

API Endpoints

Text-to-Video

Model ID: bytedance/seedance-v1.5-pro/text-to-video

Generate videos from text prompts.

Parameters

Example

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "bytedance/seedance-v1.5-pro/text-to-video",
  {
    prompt: "A timelapse of a city skyline transitioning from day to night, cinematic slow pan",
    aspect_ratio: "21:9",
    duration: 10,
    resolution: "1080p",
    generate_audio: true,
    camera_fixed: false
  }
))["outputs"][0];

Image-to-Video

Model ID: bytedance/seedance-v1.5-pro/image-to-video