# Seedance: ByteDance video AI — what 2.0 and 2.5 can do

> Seedance is a family of ByteDance Seed video models that generate a clip with sound from text, photos, video and audio. Seedance 2.0 came out on February 12, 2026 and makes 4–15 seconds. Seedance 2.5 came out on July 31, 2026: up to 30 seconds in one generation, two extensions and up to 50 references. Seedance is available in the AI2Face generator.

Developer: ByteDance Seed · Released: 2026-07-31 · Updated 2026-09-30
URL: https://ai2face.com/models/seedance

## Key facts

| | |
|---|---|
| Developer | ByteDance Seed |
| Versions | Seedance 2.5 (July 31, 2026), Seedance 2.0 and 2.0 Fast (February 12, 2026) |
| What it does | Video with sound from text, images, video and audio; editing and extending clips |
| Duration | 2.5 — up to 30 seconds per generation and two extensions; 2.0 — 4–15 seconds |
| References | 2.5 — up to 30 images, 10 videos and 10 audio; 2.0 — up to 9, 3 and 3 |
| Resolution | 2.0 — native 480p and 720p; the developer does not disclose it for 2.5 |
| Sound | Generated with the video — speech, effects, music |
| Where it runs | Jimeng and Doubao Pro, plus an API for developers |
| In AI2Face | Yes |

## What Seedance is

Seedance is the video models from the ByteDance Seed team, which also makes the image models [Seedream](/models/seedream). The idea of the family is one architecture for video and sound: the clip, speech, effects and music are generated together, not stuck on afterwards.

Seedance 2.0 came out on February 12, 2026. It was the first to take four kinds of input at once — text, images, video and audio — and it learned to edit and extend clips. A faster Seedance 2.0 Fast came out with it.

Seedance 2.5 came out on July 31, 2026 on the same architecture. The main difference is length: up to 30 seconds in one generation and two extensions. The model builds several connected shots inside the clip instead of stretching one moment.

## What Seedance can do

**Several shots in one generation.** Describe the scene shot by shot — a wide shot, a medium shot, a tracking shot — and the model assembles them into one clip with cuts and a shared soundtrack.

[A foggy fishing harbor at dawn: an elderly fisherman in a yellow raincoat unties a boat, and the boat heads out to sea toward the sun](https://ai2face.com/_astro/media/models/seedance/multi-shot-story.mp4 "Three shots from one prompt: wide, medium and a tracking shot behind the boat. Seedance 2.5, 15 s, 720p")

**A character from a reference.** In Seedance 2.5 you can upload up to 30 images, 10 videos and 10 audio files at once and say in the prompt what to take from where. The model keeps the character's face and look in a new scene.

[A woman with red curls rides a bicycle with a basket of flowers along the sea, laughs and waves at the camera](https://ai2face.com/_astro/media/models/seedance/reference-character.mp4 "The face comes from one selfie, the scene from the prompt. Seedance 2.5, 9:16, 10 s")

**Dialogue and sound.** Lines in quotes become speech with synced lips, and the model builds the shot-reverse-shot cutting between the speakers on its own.

[Two friends at a table in a noodle bar at night: the man asks, the woman laughs and answers, and the shots cut between them](https://ai2face.com/_astro/media/models/seedance/dialogue.mp4 "Two lines from the prompt, cuts between the characters and room noise. Seedance 2.5, 10 s")

**Motion and camera.** The model holds fast action: sports, jumps, drone flyovers, a slow-down at the peak.

[A snowboarder rides down fresh snow, jumps off a kicker and spins; the camera follows from behind and swings to the side](https://ai2face.com/_astro/media/models/seedance/motion.mp4 "A trick in the jump with a camera move and the sound of snow. Seedance 2.5, 8 s")

**Editing and extension.** Seedance 2.0 and 2.5 change individual fragments, characters, actions and the plot of a finished clip. 2.5 adds editing by timecode, green-screen work and control from a “white model” — a rough 3D blockout of the scene.

## Seedance 2.5 and 2.0: how they differ

| | Seedance 2.0 | Seedance 2.5 |
|---|---|---|
| Released | Feb 12, 2026 | Jul 31, 2026 |
| Length per generation | 4–15 s | up to 30 s |
| Extension | yes | two times |
| References | up to 9 images, 3 videos, 3 audio | up to 30 images, 10 videos, 10 audio |
| Several shots per pass | yes | yes, a connected story |
| Editing | fragments, characters, actions | + timecodes, green screen, “white model” |
| Faster version | 2.0 Fast | — |

ByteDance separately names the 2.5 improvements: object texture, skin and eyes, light, color saturation, and how tightly the sound matches the picture.

## What Seedance is good for

- **Short stories and ads of 20–30 seconds** without stitching several generations together.
- **Clips set to music:** upload audio as a reference for rhythm and sound.
- **A series with one character:** dozens of photos of the character in one request.
- **Sports and action:** fast movement, flyovers, slow motion.
- **Editing a finished clip:** replace a character, an action or a span by timecode.

## Seedance and alternatives

| | Seedance 2.5 | [Veo 3.1](/models/veo-3-1) | [Gemini Omni 1.1 Flash](/models/gemini-omni) |
|---|---|---|---|
| Developer | ByteDance Seed | Google DeepMind | Google DeepMind |
| Length per generation | up to 30 s | 4, 6, 8 s | 3–10 s |
| Extension | 2 times | up to 148 s (API, 720p) | up to 40 s |
| Resolution | not disclosed | up to 4K | up to 4K (upscale) |
| References | 30 photos, 10 videos, 10 audio | up to 3 images | images and up to 3 videos |
| Sound | yes | yes | yes |
| In AI2Face | yes | yes | yes |

Seedance 2.5 leads on the length of a single clip and the number of references. Veo 3.1 gives 4K and a precise first-and-last-frame mode. Gemini Omni Flash is fast and flexible about what you put in.

## How to write prompts for Seedance

- **Describe the sound in as much detail as the picture:** lines in quotes, music, the key effects.
- **For several shots, number them:** “Shot 1: wide… Shot 2: medium… Shot 3: tracking…”.
- **Name references by number.** In ByteDance's official examples: “the character from @Image 2, the scene from @Image 3, the prop from @Image 4”.
- **Test the idea on a short clip,** then make the long one once the prompt is set: 30 seconds costs several times more than 5.

```
A short story in three shots. Shot 1: a wide shot of a fishing village at dawn, fog
over the harbor, boats rocking, seagulls calling. Shot 2: a medium shot of an old fisherman
in a yellow raincoat, he unties the rope of a wooden boat, looks at the sea and smiles.
Shot 3: a tracking shot behind the boat leaving the harbor toward a golden sunrise. Sound: waves,
creaking wood, distant gulls, a rising string melody. Photorealism, 35mm film
```

## How to use Seedance in AI2Face

Seedance is available in the AI2Face generator: clips with sound up to 30 seconds, and work with references. The cost is shown before you start.

Two Google models sit in the same generator for other jobs:

- **[Veo 3.1](/models/veo-3-1)** — clips of 4–8 seconds up to 4K, with speech and effects, photo-to-video, up to 3 references, and a first and last frame.
- **Gemini Omni 1.1 Flash** — clips up to 10 seconds, image references, and a first and last frame.

If you need 4K, build a long story from several 8-second Veo 3.1 clips with one character from a reference. The cost of both Google models is shown before you start.

## Limitations

- **Real faces.** For a portrait of a real person used as a reference, ByteDance requires identity verification or legal permission.
- **Complex physics and several characters.** ByteDance itself says that the physical plausibility of complex motion, and the stability of scenes where several characters interact, still need work.
- **Detail and text.** In the Seedance 2.0 evaluation, the developer names unstable detail, rare sound distortions and inaccurate text in the frame.
- **Availability.** Officially the models run in the Chinese apps Jimeng and Doubao Pro and through an API for developers. At release, the API for 2.5 was marked “coming soon”.

## Conclusions

Seedance 2.5 is the model for long story clips: 30 seconds with sound in one generation, and dozens of references, which none of the competitors can do yet. Seedance 2.0 remains a working model for clips up to 15 seconds, with editing. Seedance is available in AI2Face. If you need 4K or a precise transition between two frames, take [Veo 3.1](/models/veo-3-1) in the same generator. A long story on Veo is built from several 8-second scenes with one character.

## FAQ

### What is Seedance?

A family of video models from the ByteDance Seed team, the maker of TikTok and CapCut. Seedance creates a clip with sound from text and references: photos, video and audio.

### How is Seedance 2.5 different from 2.0?

Seedance 2.5 makes up to 30 seconds in one generation instead of 15, takes up to 50 references instead of 15, and builds several connected shots in one pass. Texture, skin, light and sound sync are also improved.

### How many seconds of video does Seedance make?

Seedance 2.5 — up to 30 seconds in one generation, and you can extend the clip two more times. Seedance 2.0 — from 4 to 15 seconds.

### Is Seedance available in AI2Face?

Yes. Seedance is available in the AI2Face generator, and the cost is shown before you generate. For 4K and a first-and-last-frame mode, Veo 3.1 and Gemini Omni Flash are in the same generator.

### Can you upload your own face to Seedance?

With limits. ByteDance requires identity verification or legal permission if the reference is a portrait of a real person.

## Sources

- https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5
- https://seed.bytedance.com/en/seedance2_5
- https://seed.bytedance.com/en/blog/official-launch-of-seedance-2-0
- https://seed.bytedance.com/en/public_papers/seedance-2-0-advancing-video-generation-for-world-complexity
- https://ai.google.dev/gemini-api/docs/veo
- https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/