# Seedance 2.5: ByteDance's video model — 30 seconds, 50 references, timestamps

> Seedance 2.5 is a ByteDance Seed video model released on July 31, 2026. It generates a clip with sound up to 30 seconds long in one pass, at 480p, 720p or 1080p with 10-bit color, and accepts up to 50 references: 30 images, 10 videos and 10 audio clips. It can edit and extend existing clips by timestamp. Seedance 2.5 is available in the AI2Face generator.

Developer: ByteDance Seed · Released: 2026-07-31 · Updated 2026-10-27
URL: https://ai2face.com/models/seedance-2-5

## Key facts

| | |
|---|---|
| Developer | ByteDance Seed |
| Release date | July 31, 2026 |
| What it does | Video with sound from text, frames and references; editing and extending clips |
| Duration | 4–30 seconds per generation or auto; multi-round extension |
| Resolution | 480p and 720p (8-bit), 1080p (10-bit), 24 fps |
| Aspect ratio | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, or follow the input — anywhere from 0.4 to 2.5 |
| References | Up to 50 per request — 30 images, 10 videos and 10 audio clips (30 seconds total per type) |
| Speech | 11 languages, including English, Chinese, Spanish, Japanese and Arabic |
| Draft | Draft mode — a 480p preview first, then the final render with the same settings |
| In AI2Face | Yes, in the generator |

## What is Seedance 2.5

Seedance 2.5 is a video generation model from ByteDance Seed, the same team that makes the [Seedream](/models/seedream) image models. ByteDance released it on July 31, 2026. It builds on [Seedance 2.0](/models/seedance-2-0) and keeps the same architecture: picture and sound are generated together, and you can feed it text, images, video and audio at once. For the whole family, see the [Seedance](/models/seedance) overview.

The headline change is length. Seedance 2.5 produces up to 30 seconds in a single generation instead of 15, and it builds several connected shots inside one clip: setup, development, turn and resolution. You can keep extending a finished clip round after round, which is why ByteDance talks about videos "several minutes long."

The model runs in ByteDance's Chinese apps Jimeng and Doubao Pro and in its developer cloud. The API model ID is `doubao-seedance-2-5-260628`.

## What Seedance 2.5 can do

**30 seconds with sound in one pass.** Set any length from 4 to 30 seconds, or choose auto and the model picks a whole number of seconds to fit the story. Sound is generated with the picture: lip-synced speech, sound effects and music.

**Up to 50 references per request.** 30 images at up to 4K, 10 videos and 10 audio clips. Each video or audio file can run 2–30 seconds, but each type is capped at 30 seconds in total. A reference can define a character, a voice, motion, style, a location or a storyboard.

**Timestamps in the prompt.** Write "0–5s: …, 5–10s: …" and the model maps action, camera and pacing to those windows. Seedance 2.0 ignored timestamps and only followed shot numbers.

**Editing finished clips.** Add, replace or remove an object, a character, the background, subtitles, music or a voice with a plain instruction: "replace the character in @Video1 with the one from @Image1." The edit keeps the source clip's length and aspect ratio.

**Extending forward and backward.** "Extend @Video1 backward: the hero falls from the sky…" and the model generates a new opening that matches the picture and sound. For edits and extensions, ByteDance recommends MOV output, which keeps color, brightness and audio more consistent.

**Animation from a 3D blockout.** You can feed it a "clay" video: a scene built from grey primitives with no textures. The model takes motion, paths, camera and lighting from it, and the look from your prompt and images.

![A grey 3D scene made of simple shapes: a red capsule runs along the sidewalk, a blue box car drives next to it, grey box buildings and cylinder street lamps around](https://ai2face.com/_astro/clay-model.C57dBI_z_Z1HwqTd.jpg "What a clay-model reference for Seedance 2.5 looks like: primitives only, no textures or faces. The model reads motion and camera from a clip like this. Image made with Nano Banana Pro")

**480p drafts.** Draft mode first renders a cheap 480p preview so you can check the story, shots and motion. The final render reuses the same prompt, seed and references, and the preview is billed separately at the 480p rate.

**Speech in 11 languages.** Chinese, English, Spanish, Indonesian, Malay, Thai, Arabic, Portuguese, Vietnamese, Japanese and Korean.

## Seedance 2.5 vs. 2.0: what changed

| | [Seedance 2.0](/models/seedance-2-0) | Seedance 2.5 |
|---|---|---|
| Released | Feb 12, 2026 | Jul 31, 2026 |
| Length per generation | 4–15 s | 4–30 s or auto |
| Resolution | 480p, 720p, 1080p, 4K | 480p, 720p, 1080p (10-bit) |
| Aspect ratio | 6 fixed options | 6 fixed options or follow the input, 0.4 to 2.5 |
| References | 9 images, 3 videos, 3 audio | 30 images, 10 videos, 10 audio |
| Timestamps in the prompt | no, shot numbers only | yes, whole seconds |
| Multi-view character sheet in one image | not recommended | supported |
| 480p draft | no | yes |
| Output | MP4 | MP4 and MOV |
| Faster variants | Fast, Mini | none |

The two versions have a different look: the same prompt and reference produce visibly different results in 2.5 and 2.0. If a project started on 2.0, ByteDance suggests extending the 2.0 clips with 2.5 and exporting MOV, which preserves the style better than generating from scratch.

There's also Seedance 2.5 4K with native 4K and 480p drafts. As of October 2026, it's limited to selected film studios — see our [Seedance 2.5 4K](/news/seedance-2-5-4k) news story.

## What Seedance 2.5 is good for

- **A short film or ad of 20–30 seconds in one piece** — no stitching several generations together, no lighting jumps between them.
- **A series with one character.** Three angles of the character plus a voice sample, and the character stays recognizable from clip to clip.
- **Dubbing a clip into another language.** An edit replaces the speech and the lip movement and leaves everything else as it was.
- **Previs and animation from a 3D blockout.** An animator blocks the motion with simple primitives, and Seedance 2.5 renders it in the target style.
- **Fixing real footage.** Remove subtitles or a watermark, swap the background, or add an object at a specific timestamp.

![A reference sheet: the same red-haired young woman in an olive field jacket shown from the front, three-quarter and profile on a grey background](https://ai2face.com/_astro/subject-views.dlnaXEB2_1ebj0u.jpg "A three-angle character reference. Seedance 2.5 accepts sheets like this, while ByteDance advised against them for 2.0. Image made with Nano Banana Pro")

ByteDance gives practical limits: results are most stable with 1–8 characters from images and 1–5 characters from video or voice. At 9–12 characters, consistency starts to slip and you'll need retries. With more than five characters, upload each angle as a separate image rather than one sheet.

## Seedance 2.5 vs. alternatives

| | Seedance 2.5 | [Kling 3.0](/models/kling-3-0) | [Veo 3.1](/models/veo-3-1) | [Vidu Q3](/models/vidu) |
|---|---|---|---|---|
| Developer | ByteDance Seed | Kuaishou | Google DeepMind | ShengShu |
| Length per generation | 4–30 s | 3–15 s | 4, 6, 8 s | 1–16 s |
| Max resolution | 1080p, 10-bit | 4K | 4K | 1080p |
| References | 30 images, 10 videos, 10 audio | up to 7 images or elements, 1 video | up to 3 images | up to 7 images |
| Editing existing video | yes, with timestamps | yes, in Omni | extension only | extension only |
| Sound | yes | yes | yes | yes |
| In AI2Face | yes | yes | yes | yes |

Seedance 2.5 wins on single-clip length and reference count. For 4K and tight physics in short shots, go with Veo 3.1 or Kling 3.0. For anime and comic dramas with several characters, look at Vidu Q3.

## How to write prompts for Seedance 2.5

ByteDance recommends thinking like a director and writing the prompt in four layers:

1. **Reference bindings.** Name every file by upload order and role: "@Image1 is the heroine, @Video1 sets the camera move, @Audio1 is her voice."
2. **A one-line summary.** Subject + location + event + genre + camera.
3. **The plot over time.** Timestamps ("0–3s", "3–8s") or "Shot 1, Shot 2" — and for each segment, the picture, camera, action, dialogue and sound.
4. **Recurring details.** Camera angle, lighting, mood, ambient sound — anything that stays constant through the clip.

Describe what you want rather than what you don't: "an empty promenade," not "no people." The exceptions are subtitles and music — the model does understand "no subtitles" and "no background music."

If the clip has to follow a storyboard exactly, upload the frames as separate images and start the prompt with "Use Images 1 to 7 in order as keyframes." A storyboard combined into one sheet only sets the overall plot: ByteDance recommends no more than 15 panels, simple line art and no text on the sheet.

![A six-panel black line-art storyboard: a lighthouse on a cliff, a woman in a raincoat on a spiral staircase, a hand on a door handle, the lantern room, a ship in a storm seen through the window, the lighthouse beam over the sea](https://ai2face.com/_astro/storyboard.CbZwn_qi_cWgfB.jpg "A storyboard in the format ByteDance recommends: six simple line-art panels with no captions. Story and camera details go in the prompt. Image made with Nano Banana Pro")

A prompt for that storyboard:

```
Storyboard @Image1, heroine @Image2. Moody short film, 35 mm, cold blue dusk light, film grain.
Shot 1 (0-5s): wide shot of a lighthouse on a rocky cliff, waves crash below, wind howls.
Shot 2 (5-10s): the heroine in a hooded raincoat climbs a spiral staircase, her steps echo.
Shot 3 (10-13s): close-up, her hand turns a round brass door handle.
Shot 4 (13-20s): she enters the lantern room and switches on the huge lamp, a low hum rises.
Shot 5 (20-25s): over-the-shoulder view of a small ship fighting the storm through the window.
Shot 6 (25-30s): wide shot, the lighthouse beam sweeps across the sea, the ship turns toward it.
Sound: wind, rain, distant thunder, no music. No subtitles.
```

**Fixes for common failures**, from ByteDance's official guide:

- **Misspelled on-screen text.** Spell the word out letter by letter, or supply the text as an image reference.
- **Glowing eyes.** The model sometimes renders strong emotions like "furious" as glowing pupils. Use neutral wording ("surprised") and add "normal human eyes."
- **Music despite "no music."** List every variant — music, background music, score, melody — and repeat the constraint at the start and end of the prompt.
- **Subtitles despite the ban.** Don't repeat dialogue words in the description, and use the "Character's line (emotion): text" format. The reference video must be subtitle-free too.
- **Fingerprint-like textures on grass and foliage.** This happens when a reference image is larger than the output resolution. Downscale it to the video size.
- **Bubbling or echo in the audio.** Remove water, waves and echo from the prompt unless the story needs them.
- **A complex task falls apart.** Split it in two: generate from references first, then edit the result.

## How to use Seedance 2.5 in AI2Face

Seedance 2.5 is in the AI2Face generator next to [Veo 3.1](/models/veo-3-1), [Kling 3.0](/models/kling-3-0) and [Gemini Omni](/models/gemini-omni), so it's easy to compare one prompt across several models.

1. Sign up — new accounts get starter credits.
2. Open the generator, switch to video and pick Seedance 2.5.
3. Upload your references and write the prompt using the structure above. Start with a 5–8 second clip: testing an idea that way costs a fraction of a 30-second render.
4. The credit cost is shown before you start and depends on length and resolution. Credits don't expire.

You can create reference images — a character, a location, a product — in the same generator, for example with [Nano Banana Pro](/models/nano-banana-pro). Every image on this page was made that way.

## Limitations

- **No 4K.** The ceiling is 1080p. Native 4K is only in the closed Seedance 2.5 4K version.
- **Fixed aspect ratio for edits and extensions.** The model follows the source clip's aspect ratio, and for edits its length too. An edited clip can come out 0.3–0.4 seconds shorter than the source.
- **Complex physics and crowds.** ByteDance itself says the plausibility of complex motion and scenes with several interacting characters still needs work.
- **Text errors.** The model mixes up letters in on-screen text: "E" turns into "A" or "I", and similar-looking characters get swapped in Chinese.
- **Real people.** Portraits of real people are allowed as references only with confirmed rights to use them.
- **Languages.** Outside the 11 official languages, prompts and speech are less reliable.

## Bottom line

Seedance 2.5 is the pick when you need one continuous 20–30 second clip with a story, a consistent character and sound: neither Kling 3.0 nor Veo 3.1 produces that much in one generation or accepts 50 references. It's also handy for editing finished footage at a specific timestamp. If 4K or flawless physics in a short shot matters more, use [Veo 3.1](/models/veo-3-1). If budget is tight and 15 seconds is enough, look at [Seedance 2.0](/models/seedance-2-0) and its Fast variant. Start with a 5-second draft in AI2Face and stretch it to 30 seconds once the prompt works.

## FAQ

### What is Seedance 2.5?

A video model from the ByteDance Seed team, released on July 31, 2026. It generates clips with sound up to 30 seconds long from text, images, video and audio, and it can also edit and extend existing clips.

### How long are Seedance 2.5 videos?

Between 4 and 30 seconds per generation. You can also choose auto and let the model pick the length. Finished clips can be extended forward or backward, one round at a time.

### What resolution does Seedance 2.5 support?

480p, 720p or 1080p. 1080p comes in 10-bit color, and 720p is the default. Native 4K is only available in the separate Seedance 2.5 4K version for film studios.

### How is Seedance 2.5 different from 2.0?

Clips are twice as long (30 seconds vs. 15), it takes more than three times as many references (50 vs. 15), it follows timestamps in the prompt, accepts multi-view character sheets and has a draft mode. Unlike 2.0, it doesn't offer 4K.

### Which languages does Seedance 2.5 speak?

Officially 11: Chinese, English, Spanish, Indonesian, Malay, Thai, Arabic, Portuguese, Vietnamese, Japanese and Korean. Prompts and dialogue in other languages are less reliable, so test them on a short clip first.

### Is Seedance 2.5 available in AI2Face?

Yes. Seedance 2.5 is in the AI2Face generator, and you see the cost before you start a generation.

## Sources

- https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5
- https://seed.bytedance.com/en/seedance2_5
- https://docs.volcengine.com/docs/ark/seedance-2-5?lang=zh
- https://docs.volcengine.com/docs/ark/seedance-2-5-prompt-guide?lang=zh
- https://seed.bytedance.com/en/blog/official-launch-of-seedance-2-0