Skip to content
ByteDance

Seedance v1.0 Pro

Seedance v1.0 Pro is ByteDance's Pro-tier Seedance 1.0 video generation model, producing 1080p clips up to 12 seconds with advanced cinematic controls for both text-to-video and image-to-video workflows. Your use is subject to ByteDance's Terms & Privacy Policies.

Video Gentext-to-video
Use with AI GatewayView docs
import { experimental_generateVideo as generateVideo } from 'ai';


const result = await generateVideo({
  model: 'bytedance/seedance-v1.0-pro',
  prompt: 'A serene mountain lake at sunrise.'
});
Read docs
OverviewAPIAboutProvidersSimilarFAQ

Copy link to headingAbout Seedance v1.0 Pro

Seedance v1.0 Pro is the top Seedance 1.0 tier for film- and broadcast-style video production. It generates 1080p video at 24 fps with clip durations from two to 12 seconds and supports both text-to-video and image-to-video input modes. Seven aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21) cover broadcast, social, and cinema display contexts.

The Seedance 1.0 tech report describes the architecture as a unified framework that handles T2V and I2V tasks via binary mask conditioning, with Multi-modal RoPE (MM-RoPE) encoding for interleaved visual and textual tokens. This design supports native multi-shot transitions, including smooth cuts between wide, medium, and close-up compositions, without post-processing.

The tech report places Seedance 1.0 first on Artificial Analysis leaderboard rankings for both T2V and I2V tasks. Use Seedance v1.0 Pro for final delivery, client presentations, and workflows where you need Pro-tier motion fidelity and controls.

See https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=seedance-1-0-pro for full methodology and benchmark tables.