# Seedance v1.0 Pro

Seedance v1.0 Pro is Seedance 1.0's top tier for production video generation. It includes multi-shot transitions, first-and-last-frame control, and the full Pro motion stack.

- **Model ID:** `bytedance/seedance-v1.0-pro`
- **Type:** video
- **Providers:** bytedance
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/seedance-v1.0-pro

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `duration`, `fps`
- **Operations:** `text-to-video`, `image-to-video`, `first-last-frame`
- **Input modalities:** `text`, `image`
- **Output modalities:** `video`
- **Aspect ratios:** `1:1`, `3:4`, `4:3`, `16:9`, `9:16`, `21:9`
- **Resolutions:** `720p`, `1080p`
- **Durations:** `2s`, `3s`, `4s`, `5s`, `6s`, `7s`, `8s`, `9s`, `10s`, `11s`, `12s`
- **Frame rates:** `24 fps`
- **Maximum outputs per request:** Not reported
- **Maximum input images:** 2
- **Input image formats:** `jpeg`, `png`, `webp`, `bmp`, `tiff`, `gif`
- **Maximum input image size:** 30 MB

## Example

```ts
import { experimental_generateVideo as generateVideo } from 'ai';

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

## About

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.

## What to consider

For production pipelines at Pro-tier quality, verify provider concurrency limits meet your throughput requirements for time-sensitive delivery schedules. Compare rates (N/A; N/A).

## When to use

### Best For

- Final-delivery video assets for advertising, film, or broadcast where you need 1080p output and Pro-tier motion fidelity
- Image-to-video workflows that need precise compositional control
- Multi-shot sequences where native scene transitions (wide, medium, close-up) must flow without manual editing
- Genre-specific cinematic projects where film conventions, lighting, shot grammar, and pacing matter for the edit

### Consider Alternatives When

- Budget or iteration speed is the primary constraint. Use Seedance 1.0 Lite for lower-cost prototyping at comparable resolution
- Generation speed matters and some quality tradeoff is acceptable. Use Seedance 1.0 Pro Fast, which delivers approximately 3x faster generation at approximately 72% lower cost
- Audio-synchronized video with dialogue and sound effects is required. Use Seedance 1.5 Pro, which adds native audio-visual joint generation

## Best for

- **Final-delivery video assets:** Advertising, film, or broadcast work that requires 1080p output and Pro-tier motion fidelity
- **Image-to-video workflows:** Precise compositional control with first-and-last-frame conditioning
- **Multi-shot sequences:** Native scene transitions between wide, medium, and close-up compositions flow without manual editing
- **Genre-specific cinematography:** Film conventions, lighting, shot grammar, and pacing matter for the edit

## Consider alternatives

- **Budget or iteration speed:** Seedance 1.0 Lite offers lower-cost prototyping at comparable resolution
- **Faster generation:** Seedance 1.0 Pro Fast delivers approximately 3x faster generation at approximately 72% lower cost
- **Audio-synchronized video:** Seedance 1.5 Pro adds native audio-visual joint generation with dialogue and sound effects

## Frequently asked questions

### What is first-and-last-frame control in Seedance v1.0 Pro?

You specify both the opening and closing frames of the generated clip. This gives precise control over the video's visual bookends and enables consistent transitions in multi-clip sequences.

### How does Seedance v1.0 Pro differ from the Pro Fast variant?

Pro Fast generates video approximately 3x faster at approximately 72% lower cost. Choose Pro when throughput isn't time-constrained and maximum quality is the priority.

### What aspect ratios does Seedance v1.0 Pro support?

Seven ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and 9:21, spanning landscape, portrait, square, and ultra-wide formats.

### Does Seedance v1.0 Pro support image-to-video in addition to text-to-video?

Yes. Both input modalities are supported within the same model, along with optional first-and-last-frame image control.

### How was the Seedance 1.0 quality level validated?

The Seedance 1.0 tech report cites first-place rankings on Artificial Analysis T2V and I2V leaderboards.

## Links

- [Model page](https://vercel.com/ai-gateway/models/seedance-v1.0-pro)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=seedance-1-0-pro)
- [Provider pricing](https://docs.byteplus.com/en/docs/ModelArk/1544106)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.