Model explainer
What Is Seedance 2.5? Features and How to Use It (Generator Included)
Seedance 2.5 is the latest video generation AI model from ByteDance, the company that operates TikTok. Its standout features are up to 30 seconds per generation and video and audio created at the same time. Based on the official information, this page summarizes what Seedance 2.5 can do, how to use it, and how the Dreamina and Higgsfield versions differ — and the generator on this page lets you try it right away.
- Max30 s
- Resolution480P / 720P / 1080P
- AudioON
- Reference imageOK

Sign in with Google in 1 second — check in daily for free credits (up to 60 a week)What you can do for free →
The generator below comes with Seedance 2.5 pre-selected. Enter a prompt and generate (for example, 5 seconds at 720p costs 420 credits; Seedance 2.5 can only be generated with purchased credits — plans or credit packs — and the free daily check-in credits cannot be used).
Seedance 2.5 example gallery
Official examples and original prompts published by the model developer. Copy them and generate as-is.
A Fantasy Journey from Clouds to the Sea
A young girl with two hair buns pilots a pink-and-white airplane through golden clouds as dragons and whales glide beside her. She then rides a surfboard across the sea, meets a small red dragon, and finally dives into a glowing underwater world. Keep the girl, her clothing, and her fantasy companions consistent through fluid transitions.
A Woman in Blue Walking Through an Enchanted Forest
A woman in a deep blue dress slowly walks down ancient moss-covered stone steps surrounded by glowing flowers, mist, stone arches, and warm sunlight. The camera follows smoothly and moves closer while her face, clothing, and lighting remain consistent.
A Restrained Tearful Close-Up
Against a black background, a short-haired woman tries to hold back tears. Keep a frontal close-up that captures natural skin, reddened eyes, lightly trembling lips, and a tear gradually running down her cheek with restrained movement.
A Red-Dressed Dancer on a Firelit Stage
A dancer in a red dress performs controlled arm movements at the center of a dark stage. The camera pushes in from a frontal upper-body view as flames rise behind her, then cuts to a close-up of her steps and flowing skirt while keeping the motion and rhythm continuous.
What you can make with Seedance 2.5
The same look as the official samples, for scenes like these.
Up to 30 Seconds of Continuous Storytelling
Create videos up to 30 seconds while preserving identity, wardrobe, and story continuity across changing scenes.
Prompt
A young girl with two hair buns pilots a pink-and-white airplane through golden clouds as dragons and whales glide beside her. She then rides a surfboard across the sea, meets a small red dragon, and finally dives into a glowing underwater world. Keep the girl, her clothing, and her fantasy companions consistent through fluid transitions.
Stable Character and Scene Consistency
Keep faces, clothing, lighting, and environment detail stable as the subject moves and the camera advances through a fantasy scene.
Prompt
A woman in a deep blue dress slowly walks down ancient moss-covered stone steps surrounded by glowing flowers, mist, stone arches, and warm sunlight. The camera follows smoothly and moves closer while her face, clothing, and lighting remain consistent.
Subtle Emotion and Micro-Expressions
Render breathing, eye and lip movement, and gradually forming tears for restrained, natural emotional close-ups.
Prompt
Against a black background, a short-haired woman tries to hold back tears. Keep a frontal close-up that captures natural skin, reddened eyes, lightly trembling lips, and a tear gradually running down her cheek with restrained movement.
Complex Motion and Natural Camera Work
Keep the dancer's gestures, body movement, flowing skirt, and fire rhythm coherent while connecting an upper-body push-in with a close-up of her steps.
Prompt
A dancer in a red dress performs controlled arm movements at the center of a dark stage. The camera pushes in from a frontal upper-body view as flames rise behind her, then cuts to a close-up of her steps and flowing skirt while keeping the motion and rhythm continuous.
Seedance 2.5 specs
- Max duration
- 30 s
- Resolutions
- 480P / 720P / 1080P
- Audio
- with audio always included
- Typical credit cost
- ≈ 152 credits (5 · 480P)
Based on this site's offering settings. Credit cost varies with duration and resolution.
What is Seedance 2.5?
Seedance 2.5 is a video generation model developed by ByteDance's research team Seed, officially announced on July 31, 2026. It builds on the previous generation Seedance 2.0 and its approach of creating video and audio together: the maximum length per generation grew from 15 to 30 seconds, and the amount of reference material you can use increased significantly.
- Announced
- Officially announced on July 31, 2026
- Official cloud release
- August 7, 2026 (the enterprise API opened)
- Video length
- Up to 30 seconds per generation (Seedance 2.0 was 15 seconds)
- Resolution
- 480p / 720p / 1080p (the API maximum is 1080p)
- Audio
- Video and audio generated together
- Reference inputs
- Up to 30 images, 10 videos and 10 audio clips
* ByteDance has also introduced 4K (3840×2160) output and the faster Seedance 2.5 Flash tier. On this site, 480p–1080p and Seedance 2.5 Flash are available right now, and 4K support is in preparation.
Seedance 2.5 4K & Seedance 2.5 Flash
Pick the 2.5 tier that fits your resolution target, turnaround speed, and credit budget.
Seedance 2.5 4K (3840×2160 Ultra-HD)
ByteDance has begun rolling out 4K (2160p) output for Seedance 2.5 while keeping 30-second single takes, synced audio, and multimodal references. On this site, 480p (38 credits/s), 720p (84 credits/s), and 1080p (211 credits/s) are live now, with 4K support in preparation.
Seedance 2.5 Flash (Faster & Lower Cost)
A streamlined tier tuned for 480p (25 credits/s) and 720p (55 credits/s). It supports 4–30s generation, native synced audio, and multimodal references (up to 10 images, 5 videos, 5 audio clips) for rapid iteration—ready to use now on this site.
Key features of Seedance 2.5
1. Up to 30 seconds in a single take
Because it can generate up to 30 seconds without cutting to a new take in the middle, it has become easier to complete a product introduction or a short story in one video. You can also extend it by generating a continuation.
2. Generates video and audio at the same time
Sound effects, ambient sound and spoken lines can be created together with the visuals in one pass. This reduces the work of adding sound afterwards and lets you finish short videos for social media quickly.
3. A large amount of reference material
Up to 30 images, 10 videos and 10 audio clips can be used as references. A character's appearance, camera work, the mood of the music and more can be directed through reference material.
4. Partial editing, green screen and clay render
Supports partial editing at specified timestamps, continuation generation (extending multiple times), and generation that uses green-screen or clay-render (untextured white model) footage as a reference.
What it is not good at
The vendor itself lists the physical realism of complex motion and the stability of scenes where several subjects interact as open challenges. For intense action or scenes with many interacting people, we recommend trying a few takes at shorter durations.
How to use Seedance 2.5
Choose where to use it: On Sesshu, you can use it right away from the generator on this page, in your language.
Choose the mode: For text only, use text to video; to specify the first frame's image, use image to video. When you want to direct a character or a mood through reference material, use the reference mode.
Write the prompt: Beyond "who does what, where", including camera movement (zoom in, follow, aerial shot) and sound (rain, cheering, spoken lines) makes the most of Seedance 2.5's simultaneous audio generation.
Test short, then go long: First check the composition at around 5 seconds and 480p–720p; if you like it, raising the duration or the resolution keeps costs down.
For how to write prompts, the prompt examples on this site are also helpful.Prompt examples
Dreamina vs Higgsfield: what differs
| Dreamina (ByteDance official) | Higgsfield | Sesshu | |
|---|---|---|---|
| Positioning | ByteDance's official creative tool | An overseas video platform with multiple video models | A video generation site with a Japanese UI |
| Seedance 2.5 | Available | Available | Available |
| Pricing | Paid plans available | Paid plans available | Credit-based (see the pricing page) |
| More info | See how to try it for free | See how to try it for free | See how to try it for free |
* For the latest pricing and terms of each service, please check each service's official website. This page lists no amounts.
Explore other models
Switch between the video generation models in one workspace. Pick by strength — the credit table below has the cost.
Compare the Seedance models
Which one in the series? Compare resolution, length, audio and price.
| Capability | Seedance 1.0 Pro Fast | Seedance 1.5 Pro | Seedance 2.0 Mini | Seedance 2.0 | Seedance 2.5 Flash | Seedance 2.5 |
|---|---|---|---|---|---|---|
| Resolution | 480P / 720P / 1080P | 480P / 720P / 1080P | 480P / 720P | 480P / 720P / 1080P | 480P / 720P | 480P / 720P / 1080P |
| Length | 2–12 s | 4–12 s | 4–15 s | 4–15 s | 4–30 s | 4–30 s |
| Audio | None | On / off | On / off | On / off | On / off | On / off |
| Reference input | Text + 1 first frame | Text + reference image | Text + reference image | Text + reference image | Text + reference image | Text + reference image |
| Lowest price | 6 credits (2s, 480P) | 18 credits (4s, 480P) | 20 credits (4s, 480P) | 104 credits (4s, 480P) | 100 credits (4s, 480P) | 152 credits (4s, 480P) |
| Best for | Cheap, fast drafts | HD with audio | Affordable multimodal | Flagship multimodal | Faster generation | Flagship multimodal |
Estimates based on this site's settings. Check the amount shown in the generator before generating.
Seedance 2.5 pricing
Credits by resolution and length.
| Resolution | Per second | 5s | 10s |
|---|---|---|---|
| 480P | 38 | 190 | 380 |
| 720P | 84 | 420 | 840 |
| 1080P | 211 | 1055 | 2110 |
Estimates based on this site's settings. Audio and reference media may change the amount.
Buy credits and generate right away.
See plansFAQ
Where can I use Seedance 2.5?
You can use it right from the generator on this page. Seedance 2.5 is also offered through services built on ByteDance's model.
Is the Seedance 2.5 on Dreamina a different model from the Seedance 2.5 on other platforms?
Both are services built on ByteDance's Seedance 2.5. The differences are in how each service is offered: pricing, free allowances, the interface and so on. Dreamina is ByteDance's official tool; Higgsfield is a platform that bundles multiple models.
Can Seedance 2.5 output 4K?
ByteDance has started rolling out 4K (3840×2160) support for Seedance 2.5. On this site, you can generate at 480p, 720p, and 1080p today, and 4K support is in preparation.
How long a video can Seedance 2.5 make?
Up to 30 seconds in one generation (the previous generation, Seedance 2.0, was 15 seconds). You can also extend a video by generating a continuation.
Are "seedance2.5" and "Seedance 2.5" the same thing?
Yes, they are the same model. The spellings "seedance2.5" and "Dreamina Seedance 2.5" are also used as variants.
What is the difference between Seedance 2.5 and Seedance 2.5 Flash?
Seedance 2.5 is the flagship tier supporting up to 1080p, while Seedance 2.5 Flash focuses on 480p and 720p for faster generation at fewer credits per second. Both support up to 30 seconds, synced audio, and multimodal references.



