Newest released Seedance
Seedance 2.5 AI Video Generator
Seedance 2.5 tells a short story in one take: up to 30 seconds, several connected shots, sound included. Write a prompt, add a picture or references, and render it here.
- 4–30 s per clip
- 480P · 720P · 1080P
- Sound included
- Text · image · reference
- Refund if it fails
Renders from this site
Each clip lists the model and the exact prompt it was made with. Start from one and change what you like.
“Shot 1: close-up of an old lighthouse keeper in a wet oilskin coat climbing a spiral iron staircase, a swinging lantern lighting his face, rain hammering the windows. Shot 2: wide shot from the sea as the lighthouse beam sweeps across huge storm waves crashing on the rocks, lightning splits the sky. Rolling thunder and howling wind”
Text · 2.0 · 720P · 5s
Use this prompt“Close-up of a young barista with a dark apron behind a café counter, she looks up from the espresso machine, smiles warmly and says "Your usual?". Soft morning light, shallow depth of field, café chatter and an espresso machine hissing in the background”
Text · 2.0 · 720P · 5s
Use this prompt“A street dancer in a yellow hoodie spins and drops into a freeze on a city rooftop at dusk, skyline lights coming on behind her, the camera circles her in one smooth orbit, a punchy hip-hop beat”
Text · 2.0 · 720P · 5s
Use this prompt“A red paper boat drifts down a rain-soaked city gutter at night, neon reflections, the camera follows low and close, soft rain sounds”
Text · 2.0 Fast · 480P · 5s
Use this prompt
What Seedance 2.5 changes
ByteDance Seed released Seedance 2.5 on July 31, 2026, describing it as built for 30-second storytelling. The main change from 2.0 is length: one generation now runs up to 30 seconds instead of 15, and the model plans several linked shots inside it, so a clip can have a beginning, a turn and an end.
ByteDance also lists more references (up to 30 images, 10 clips and 10 audio files per generation), extending a clip in rounds, and editing by timestamp. On Seedance 3 AI you generate new clips from a prompt, a first and last frame, or up to 9 images, 3 clips and 3 audio files. Editing and extending aren't offered here.
Use 2.5 when the extra length matters: a product spot with problem, product and payoff; a scene with a few lines of dialogue and a reaction; a travel clip that moves through several places. Split the prompt into timed beats such as 0–10 s, 10–20 s and 20–30 s, and repeat the details that must stay the same, like a character's face, clothes and the light.
It costs more per second than 2.0, and the bill grows with every second, so test the beats at 480P or at a shorter length first, then render the final at 720P or 1080P. For clips of 15 seconds or less, Seedance 2.0 is usually the better value.
Seedance 3 AI is independent and not affiliated with or endorsed by ByteDance. Seedance, Dreamina, Jimeng and Doubao are trademarks of their owners.
- Model
- Seedance 2.5
- Resolution
- 480P · 720P · 1080P
- Length
- 4–30 s
- Credits per second
480P14/s
720P31/s
1080P75/s
How to make a Seedance 2.5 video
Nothing to install and no invite to wait for. Most clips are ready in a few minutes.
- 01
Write the shot
Who is in it, what they do, how the camera moves, the light and what we hear. Or open an example and edit it.
- 02
Add an image or references
Optional: a first or last frame, or reference images, clips and audio for the model to follow.
- 03
Pick a model and render
Choose 2.0 Fast, 2.0 or 2.5, the resolution and the length. The button shows the credits; download the MP4 when it's done.
Which Seedance model to use until 3.0
All three take the same inputs and make sound. They differ in price, top resolution and length.
| 2.0 Fast | 2.0 | 2.5 | |
|---|---|---|---|
| Resolution | 480P, 720P | 480P, 720P, 1080P | 480P, 720P, 1080P |
| Length | 4–15 s | 4–15 s | 4–30 s |
| Inputs | Text, frames, references | Text, frames, references | Text, frames, references |
| Typical wait | Fastest, about 2 minutes | A few minutes | A few minutes; 30 s takes longer |
| Price | From 6 credits/s | From 10 credits/s | From 14 credits/s |
More ways to create
Seedance 3 AI home
Every Seedance model in one generator, plus Seedance 3 status.
Seedance 3.0
Release status, facts vs rumors, and what to use now.
Text to video
Write the shot, get a video with sound.
Image to video
Animate a picture, with an optional end frame.
Reference to video
Images, clips and audio steer character, scene and voice.
Seedance 2.5 questions
The newest released model in ByteDance's Seedance family, launched on July 31, 2026. It makes videos with sound from text, images, clips and audio, up to 30 seconds per generation.
Any whole number of seconds from 4 to 30. You set the length before you generate, and the price updates with it.
2.5 for anything over 15 seconds or with several story beats. 2.0 for short clips: it's cheaper per second and also reaches 1080P. 2.0 Fast is cheaper still for drafts.
Write it as timed beats, "0–10 s: …, 10–20 s: …, 20–30 s: …", one main action per beat, and restate the character's look in each. Spoken lines go in quotes. The prompt guide on our blog has worked examples.
It's billed per second and by resolution, up to 75 credits a second at 1080P. The button shows the total before you generate.
Not on this site. ByteDance offers timestamp editing and extension in its own apps; here you generate new clips. To continue a scene, use a still from the end of one clip as the first frame of the next.
No. Seedance 3 hasn't been released. 2.5 is the newest version available, and when Seedance 3 comes out it will be listed here as a separate model.
No. Seedance 3 AI is an independent site that runs Seedance 2.5 through an API. ByteDance's own page for the model is seed.bytedance.com/seedance2_5.
Make a 30-second Seedance video
Write one sentence, choose a length and get a video with sound. Your first one is free.
Start creating