English 繁體中文 简体中文

How to use Seedance 2.5 for text-to-video (version 1)?

Howard Pong Yuen Lam · AI Notes · November 8, 2026 · 5 min read

Seedance 2.5 is ByteDance’s AI that turns written words into a short video. You type a description — called a prompt — and it makes the clip for you. No camera, no editing software, no filming skills needed. You can try it on ByteDance’s Jimeng website.

The whole skill is knowing what to write. This note shows the six-part formula behind every good Seedance prompt, a template you can copy and fill in, and one complete example. Write your prompt in English or Chinese — Seedance understands both.

What you need before you start

The core prompt formula

Every Seedance prompt is built from six parts. The first two are required; the other four are optional — add them only when you care about them. (Source: ByteDance’s Seedance 2.5 prompt guide and prompt examples.)

Subject + Action or Event
+ Scene and Environment (optional)
+ Visual Style (optional)
+ Camera Movement/Cut (optional)
+ Audio (optional)

A template you can copy

Replace each part in angle brackets with your own words. (Source: ByteDance’s Seedance 2.5 prompt guide and prompt examples.)

<Subject> performs <primary action or event> in <scene and environment>.
The visuals feature <visual style>.
Use <shot size, camera angle, camera movement, or cuts>.
Audio includes <dialogue, ambience, sound effects, or music>.

Leave out a sentence completely if you do not need that part — a two-line prompt (subject and action only) is a perfectly good start.

A worked example

Here is a complete prompt that uses all six parts — a ceramic artist finishing a cup. It is the worked example from ByteDance’s own Seedance 2.5 materials. (Source: ByteDance’s Seedance 2.5 prompt guide and prompt examples.)

A ceramic artist finishes a pale blue cup in a studio at dawn, lifts it
from the wheel, and places it in the center of a wooden shelf.
Soft morning light enters through the window. The wet clay has a delicate
sheen, and the workbench remains tidy.
Begin with a medium shot of the wheel-throwing process, slowly push in
toward the cup's surface texture, then cut to a frontal view of the shelf.
Retain the low hum of the pottery wheel, the friction of clay, and subtle
indoor ambience.

Line by line, this is just the formula with the blanks filled in:

Watch the demo video

Open in Google Drive (no account needed).

The 56-second recording shows the whole flow: the ceramic-artist prompt (in Chinese) is pasted into Jimeng, the AI loads its video-prompt skill and thinks for a moment, then the finished clip plays — the potter at the wheel, the slow push-in on the cup’s surface, and the cut to the shelf, exactly as the prompt asked. The “AI生成” (“AI-generated”) mark in the corner of the clip is added by the platform.

Good to know

Further reading