Mina LabsSeedance 2.5 AI Video Generator
Seedance 2.5 is ByteDance's newest video model and the one to reach for when a shot needs to breathe: native single-shot clips up to thirty seconds, far past where most models cut off, in text to video, image to video and reference to video at 480p or 720p with audio. It sits above the older Seedance 2.0 Mini, Fast and Premium tiers, and every clip's price is shown before you spend.
Open the Studio → pay per generation · no subscription · failed generations refundedWhat it costs
| Model | Credits | Per |
|---|---|---|
| Seedance 2.5 (Text to Video) | 69 credits | 5s at 720p |
| Seedance 2.5 (Image to Video) | 69 credits | 5s at 720p |
| Seedance 2.5 (Reference to Video) | 69 credits | 5s at 720p |
Prices come from the same table the Generate button uses. You pay per generation; failed generations are refunded automatically.
How it works
- Open the Video StudioSign in: pay per generation, no subscription.
- Pick Seedance 2.5 and a modeSelect Seedance 2.5, then choose text, image or reference to video. The credit price shows on the Generate button.
- Add your inputsWrite the prompt; for image or reference modes, upload your starting frame or reference images.
- Set length and resolutionChoose up to 30 seconds and 480p or 720p; the price updates to match.
- Generate and saveRun it in the background, then preview and save the clip from your Library.
Questions
What is new in Seedance 2.5?
Seedance 2.5 by ByteDance generates native single-shot clips up to 30 seconds: far longer than most models: in text-to-video, image-to-video and reference-to-video, at 480p or 720p with native audio. It is the newest Seedance on Mina Labs, above the Seedance 2.0 Mini, Fast and Premium tiers.
How long can a Seedance 2.5 clip be?
From 4 up to 30 seconds in one shot, at 480p or 720p. The exact credit price for your length and resolution shows on the Generate button before you spend.
Can Seedance 2.5 keep a character consistent?
Yes: Reference to Video takes reference images you cite in the prompt as @Image1, @Image2 and keeps the character, set and palette consistent across the clip.