# Seedance 2.5 and Seedance 2.0

> Run ByteDance Seedance 2.5 and Seedance 2.0 in Faceless: 5 to 15 second clips up to 1080p with dialogue, sound effects and music made in the same pass. Prices in credits, a real sample, and a prompt box.

Canonical: https://faceless.so/models/seedance
Last updated: 2026-11-12

AI model

ByteDance's video model, with the sound made in the same pass. Run it in Faceless from a prompt or your own picture.

Updated November 12, 2026 · By Faceless

## Seedance is ByteDance's AI video model, and Faceless runs Seedance 2.5 and 2.0

**Seedance 2.5 turns a prompt into a 5, 10 or 15 second clip at 480p, 720p or 1080p, with dialogue, sound effects and music made in the same pass.** A 5 second clip is 63 credits at 720p (28 at 480p, 158 at native 1080p), and sound costs nothing extra. Type a prompt below and it opens in the Faceless Text to Video studio with Seedance 2.5 already picked.

Seedance 2.0 runs in its own tool, where reference images, videos and audio steer the clip. And every narrated Faceless short on the Motion tiers is made of Seedance clips.

Made with Seedance 2.5 in the Faceless Text to Video studio: 5 seconds, 480p, 9:16, sound off. Prompt: "A paper boat drifting across a calm pond at dawn, watercolor illustration, gentle ripples"

## Seedance 2.5 or Seedance 2.0: which to use

-   **Seedance 2.5** (Text to Video studio): a prompt, or a prompt and your first frame, in. 5, 10 or 15 seconds, up to native 1080p, in 6 shapes (16:9, 4:3, 1:1, 3:4, 9:16, 21:9), with sound. It can also star up to 3 of your saved [characters](https://faceless.so/characters).
-   **Seedance 2.0** ([its own tool](https://faceless.so/seedance2/create)): up to 5 reference images, 3 reference videos and 3 audio files steer a 4 to 15 second clip at 480p, 720p or 1080p. Use it when you need the clip to follow a motion or a sound you already have.

**Start on Seedance 2.5 at 480p or 720p.** Get the motion right on the cheap step, then make the keeper at 1080p, which costs about 2.5 times the 720p clip.

## What Seedance costs: 28 to 474 credits a clip

Seedance 2.5 in the Text to Video studio, by clip length and resolution. Sound is included in every price:

Seedance 2.5 credits for each clip length and resolution

Seedance 2.5

5s clip

10s clip

15s clip

480p

28

56

84

720p

63

126

189

1080p

158

316

474

Seedance 2.0 is priced by the second: 9 credits at 480p, 18 at 720p and 40 at 1080p. With reference videos it is 5, 14 and 31 credits a second, counted over the reference videos plus the clip.

Credits come with every plan. Starter is $29 a month for 500 credits, about 7 five second Seedance 2.5 clips at 720p. See [pricing](https://faceless.so/pricing) for the other plans.

## Where Seedance runs in Faceless

1.  **Text to Video studio.** Open [Text to Video](https://faceless.so/text-to-video/create), pick Seedance 2.5 in the Model menu, write the prompt and set the length, resolution and shape. The box above opens it with Seedance 2.5 already picked.
2.  **Seedance 2.0 tool.** Open [Seedance 2.0](https://faceless.so/seedance2/create), add your reference images, videos or audio, and set the resolution, shape and length.
3.  **Narrated shorts and series.** Pick [Motion](https://faceless.so/create?source=Facts%20%26%20stories&model=motion) (2 credits a second, Seedance 2.0 mini) or [Motion Max](https://faceless.so/create?source=Facts%20%26%20stories&model=motion_max) (6 credits a second, Seedance 2.5) as the visual style of a short. Faceless writes the script, voices it, makes a Seedance clip for each scene, captions it and can post it every day.

## How to write a Seedance prompt

-   **Write the action as beats.** Seedance follows several actions in order: "he lifts the lid, steam rolls out, he leans in".
-   **Put speech in double quotes.** Seedance voices it. English and Spanish come out clean.
-   **Name the sound you want.** "Rain on a tin roof, distant thunder" gives you that bed under the picture.
-   **Give the camera a verb.** Push in, track left, orbit, handheld. One move a clip reads best.

## When another model fits better

For silent 1080p B-roll at the lowest price, [Kling 2.5 Turbo](https://faceless.so/models/kling) costs less a clip. For film-style realism with dialogue, [Veo 3.1](https://faceless.so/models/veo) is the other model with sound. All of them sit in the same studio menu, so you can make the same prompt on two and keep the better one.

## Seedance questions

Versions, length, sound and credits

### What is Seedance?

Seedance is ByteDance's AI video model. It turns a text prompt, or a prompt plus a starting picture, into a short video clip, and its newer versions make the sound (dialogue, sound effects and music) in the same pass as the picture. Faceless runs Seedance 2.5 and Seedance 2.0.

### Is Seedance 2.0 free on Faceless?

Signing up is free, but making a clip uses credits, which come with a plan (from $29 a month for 500 credits on Starter). A 5 second Seedance 2.5 clip is 28 credits at 480p and 63 at 720p. Seedance 2.0 is 9 credits a second at 480p.

### How long can a Seedance video be?

Seedance 2.5 makes 5, 10 or 15 second clips. Seedance 2.0 makes 4 to 15 seconds. For a longer video, a Faceless short on the Motion tiers strings many Seedance clips together under a voiceover and captions.

### Does Seedance make sound?

Yes. Seedance 2.5 makes dialogue, sound effects and music with the clip, at no extra credit cost. Write spoken lines in double quotes. Speech is reliable in English and Spanish; ByteDance lists other languages that we have not measured.

### What is the difference between Seedance 2.5 and Seedance 2.0?

Seedance 2.5 is the newer model and the one in the Text to Video studio: a prompt or a first frame in, a clip with sound out, up to native 1080p. Seedance 2.0 runs in its own tool, where you can give it up to 5 reference images, 3 reference videos and 3 audio files to steer the result.

### Can I start a Seedance clip from my own picture?

Yes. In the Text to Video studio, add a picture and Seedance 2.5 opens the clip on it. Turn on Loop and the end of the clip dissolves back into your picture, which makes a seamless loop.

### Can Seedance make a whole faceless video?

A single clip is 15 seconds at most and has no narration. For a full short with a script, AI voiceover and captions, Faceless uses Seedance on its Motion tiers: Motion runs Seedance 2.0 mini at 2 credits a second of video, Motion Max runs Seedance 2.5 at 6.

## Other models in Faceless

[Kling 3.0 and 2.5 Turbo Photoreal people and 1080p motion from Kuaishou.](https://faceless.so/models/kling)

[Veo 3.1 and Veo 3.1 Fast Google's video model with dialogue and sound design.](https://faceless.so/models/veo)

[Nano Banana Pro and Nano Banana 2 Google's image model that spells text right.](https://faceless.so/models/nano-banana)

[GPT Image 2.5 and GPT Image 2 OpenAI's image model for photoreal scenes and long briefs.](https://faceless.so/models/gpt-image)

## Ready to Create Your Own Videos?

Start creating amazing AI-powered faceless videos in minutes with Faceless

[Start my channel](https://faceless.so/projects)[View Pricing](https://faceless.so/pricing)

Free to sign upPlans from $29/moCancel anytime
