Tomato AI LogoTomato AI
Home
Video AI
Pricing-50%
Blog⚽ World CupHOT
←
Tomato AI LogoTomato AI

Tomato AI integrates Jimeng 3.0, Veo 3.1, Sora 2, Kling 3 and other top models. Deliver commercial-grade videos from text, images or video in seconds.

Product

  • Text to Video
  • Image to Video
  • 关于我们

Resources

  • Pricing
  • FAQ
  • Blog

© 2026 • Tomato AI All Rights Reservedsupport@tomato.ai
Terms of ServicePrivacy Policy
Tomato AI is an independent product and is not affiliated with ByteDance, Google, OpenAI, etc.
← Back to Blog
prompt engineering

Seedance 2.0 Prompt Standards & Advanced Formula

2026-06-0810 min readTomato AI Team

Seedance 2.0 Prompt Standards & Advanced Formula

Overview

A great prompt isn't just descriptive copy — it's an engineering instruction. Seedance 2.0 is essentially a multi-modal AI director: it reads your text prompts, images, videos, and audio simultaneously, then breaks them down into a "spatial layer" (what's in the frame) and a "temporal layer" (how things change over time) to understand and generate the video.

This article covers three dimensions to help you build high-quality prompts: the Advanced Formula Framework, Language Standards, and Special Character Standards. Using them together significantly improves the accuracy and consistency of your results.


1. Advanced Prompt Formula

Core Formula

Advanced Prompt Formula:

Precise Subject + Action Details + Scene Environment + Lighting & Tone +
Camera Movement + Visual Style + Quality + Constraints

Writing Process

  • Lock "who" is doing "what" → Define subject + action description
  • Set "where" and "what mood" → Scene environment + lighting & tone
  • Tell the model "how to shoot" → Camera movement
  • Tighten the result → Style + quality + constraints

Summary

First lock who is doing what, then set where and what mood, then tell the model how to shoot, and finally tighten the result with style, quality, and constraints.


2. Language Standards

Core Rule

Dialogue language must be consistent — avoid mixing Chinese and English (except for proper nouns).

#### Correct Examples

{今天天气真好}  ✓
{How are you}   ✓  (English is fine in English-only scenes)

#### Incorrect Examples

{今天天气真好, you know}  ✗  (mixing Chinese and English)

Non-English Dialogue

If dialogue is in a language other than Chinese or English, specify the language.

#### Examples

She says in Japanese{こんにちは}
He says in Korean{안녕하세요}

3. Special Character Standards

Overview

Using symbols appropriately in prompts helps the model accurately distinguish different types of information.

Symbol Reference Table

Info TypeSymbolExample
Music()(Upbeat rock music playing in the background)
Sound Effect<>
Dialogue{}{Hello, world}
Subtitle【】【Chapter 1: Departure】

Usage Examples

<metallic scraping sound>           # Sound effect
(background music crescendo)        # Music
{How did the exam go?}             # Dialogue
【Chapter 1: Departure】           # Subtitle

Non-Language Dialogue Rule

If dialogue is in a non-Chinese/English language, specify the language:

She says in Japanese{こんにちは}

Tip: When combined with the advanced formula, place special characters in the corresponding element position. For example, use {} for dialogue in action descriptions, and () for background music in scene environments.


Summary

Best results come from using all three standards together:

StandardPurposeKey Points
Advanced FormulaProvides the overall prompt frameworkSubject → Action → Scene → Lighting → Camera → Style → Quality → Constraints
Language StandardsEnsures dialogue is clear and consistentNo mixing languages, specify non-English
Special CharactersHelps the model distinguish info types{} dialogue, <> SFX, () music, 【】 subtitles

Master these three standards to build a complete toolkit for crafting high-quality Seedance 2.0 prompts — from framework construction to detail refinement, every step has a clear guideline.

🍅 Try AI Video Generation Free on Tomato AI

Sign up for free credits. Access Seeddance 2.0, Sora 2, Kling 3 & more top models. No watermark, 1080P output.

Start Creating Free →