Seedance 2.0 Turbo
Fast, lower-cost ByteDance video model with native audio, 4 to 15 second clips up to 720p.
Made with Seedance 2.0 Turbo
Sample outputs. Open in Studio to generate your own.
Where Seedance 2.0 Turbo shines
Quick Drafts
Iterate on short concept clips of 4 to 15 seconds at a lower per-second cost before committing to a higher-detail model.
Image to Video
Animate a still by supplying a first-frame image, with an optional last-frame image to guide the motion to a chosen end state.
Sound on Clips
Generate video with native audio in one pass thanks to the built-in audio toggle that is on by default.
Strengths
- Native audio generation built in, so clips can ship with sound from a single generation
- Image-to-video with first-frame input plus an optional last-frame image for first-to-last-frame interpolation
- Multimodal Edit mode accepts up to 9 reference images, 3 reference videos, and 3 reference audio clips
- Wide duration range from 4 to 15 seconds in one-second steps
- Broad aspect-ratio coverage: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and adaptive
- Fast, lower-cost tier of the Seedance 2.0 family aimed at iteration and batch drafts
Trade-offs
- No native 1080p output; maximum resolution is 720p
- Priced per second of output, so cost scales with clip length
- Reference videos add an extra per-second surcharge on top of the base resolution rate
- Lower detail than the full Seedance 2.0 (Pro) model
- Reference images, videos, and audio are only available in Edit mode, not the default Generate mode
- Reference audio requires at least one reference image or video to be present
At a glance
About Seedance 2.0 Turbo
Seedance 2.0 Turbo is the fast tier of ByteDance's Seedance 2.0 video family, built for quick iteration and high-volume drafts. It generates clips from 4 to 15 seconds in one-second steps, at 480p or 720p, and exports in MP4. Native audio generation is built in and on by default, so your clips can ship with sound from the start.
The model covers text-to-video and image-to-video, including first-frame inputs with an optional last-frame image for first-to-last-frame interpolation. Its Edit mode is multimodal: it accepts up to 9 reference images, up to 3 reference videos, and up to 3 reference audio clips to steer the result. Aspect-ratio coverage is broad, spanning 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and an adaptive option for vertical, square, and cinematic framing.
Compared with the full Seedance 2.0 (Pro), Turbo trades some detail and the 1080p ceiling for lower cost and faster turnaround. Pricing is per second of output and tiered by resolution, so 720p costs more per second than 480p, with an additional surcharge when reference videos are used. Run it on HexGen by picking a mode, writing your prompt, and adding reference media when you need finer control.
Starting points
Copy, tweak, and run. Good prompts get you most of the way there.
A neon-lit street market at night, rain reflecting on the pavement, slow camera dolly forward, ambient crowd chatter and distant music, 9:16, 8 seconds.
Animate this product photo: the bottle rotates slowly on a marble surface under soft studio light, gentle highlight sweep, 1:1, 6 seconds.
First frame: a still mountain lake at dawn. Last frame: the same lake with full sunrise glow. Smooth interpolation, birdsong audio, 16:9, 10 seconds.
Pay only for what you render. 1 USD = 1,000 HGcoins. HGcoins never expire and failed runs refund automatically.
Seedance 2.0 Turbo vs other models
Seedance 2.0 Turbo is the fast, lower-cost tier of ByteDance's Seedance 2.0 video family. Here is how it stacks up against the full Seedance 2.0 and a Kling video model.
| Model | Quality | Speed | Cost | Choose it when |
|---|---|---|---|---|
Seedance 2.0 Turbo This ByteDance | Great | Fastest | Lower cost | Pick Turbo for fast, low-cost drafts and high-volume iteration with native audio, when 720p is enough. |
ByteDance | Best | Fast | Higher cost | Step up to the full Seedance 2.0 (Pro) when you need higher detail and native 1080p output. |
Kuaishou | Best | Fast | Mid cost | Consider Kling 2.6 as an alternative video engine when you want a different generation style. |
Related models
Frequently asked questions
It generates short AI videos from text or from images, supporting text-to-video and image-to-video, with native audio that is on by default. Clips run 4 to 15 seconds at 480p or 720p and export as MP4.