03:00:0017% OFF領取
Seedance 2.0 提示詞指南

Seedance 2.0 Prompt Guide

一個真正的內頁式指南:講清 Seedance 提示詞寫法、如何分配多模態參考素材,並用真實 Output / Reference Input / Prompt 案例做對照。

Prompt
Reference
Output

聯網調研整合

官網和三方指南共同強調的創作方式

最強的 Seedance 指南都在重複同一件事:先選工作流程,再寫提示詞;每個素材都要有明確職責;描述影片時要寫動作和鏡頭,而不只是寫一張漂亮畫面。

01

Choose the workflow first

Use text-only for concepts, image input for identity and product shape, video input for timing, and audio input for rhythm or mood.

02

Put shot structure up front

For complex clips, state the duration, aspect ratio, shot count, and shot order before the cinematic details.

03

Give each reference a job

Write whether Image 1 locks identity, Video 1 controls movement, or Audio 1 controls pacing. Do not leave reference roles implicit.

04

Debug one failure at a time

If the result drifts, change only the identity note, motion note, camera note, or constraint. Small revisions are easier to judge.

01 General Tips

1.1 Basic Prompt Formula

Seedance 對自然語言理解很強,但短影片仍然需要明確導演指令。每條提示詞都可以從下面這些可控部件開始搭。

Required

Subject

Name the person, product, place, or object that the clip must keep readable.

Required

Motion

Give the subject one clear action, then add timing only when the action changes.

Optional

Environment

Set the physical location, weather, props, background movement, and spatial depth.

Optional

Aesthetics

Describe lens feel, color grade, lighting, texture, genre, and production quality.

Optional

Camera

Use film verbs such as dolly in, orbit, locked-off, handheld, tracking, crane, or macro.

Optional

Audio

Add ambience, dialogue, music mood, voiceover, subtitles, or sound-effect timing.

1.2 Multimodal Reference Control

1.2 Multimodal Reference Control

用影像鎖身份和形狀,用影片鎖動作與鏡頭節奏,用音訊提示節奏或氛圍。不要只上傳素材,要告訴模型每個素材負責什麼。

目前工作台限制

這些數值來自專案裡的真實生成器設定。

Output duration

4-15s

Ratios

Auto, 16:9, 9:16, 4:3, 3:4, 21:9, 1:1

Resolution

360p, 480p, 512p, 540p, 720p, 768p, 1080p, 4k

Images

up to 9

Videos

up to 3, 15s total

Audio

up to 3, 15s total

案例庫

Output / Reference Input / Prompt examples

每個案例都按內頁指南的方式組織:先看生成結果,再看參考輸入,最後給出可改寫的提示詞。

02

Text in Video

2.1 Slogan / Title Text / 2.2 Subtitles / 2.3 Speech Bubbles

Output
Text to Video

2.1 Slogan / Title Text

Animated Slogan With Product End Card

Use the last beat of a product story for a short title card or slogan. Keep the phrase simple and say exactly when it appears.

Formula

[Text content] + [appearance timing] + [position] + [text style]

Reference Input
Bread craft commercial reference frame
Image 1 - Product mood frameImage
Prompt
Create a 15-second premium food commercial. Show a disappointed customer, a quick flashback of hand-made craft, then a warm close-up bite. At the final 2 seconds, blur the background and place bold gold text in the center: "REAL BREAD. REAL CRAFT." Keep the text large, readable, and stable.

控制重點

  • Use common characters and short words.
  • Tell the model where the text appears.
  • Reserve text for one clear moment.
使用這個工作流程
Output
Reference to Video

2.2 Subtitles

Narrated Deck With Subtitles

Subtitles work best when the narration is short and the visual sequence is already organized into slides or beats.

Formula

[Voiceover line] + [subtitle position] + [sync timing] + [slide order]

Reference Input
PPT slides used as reference
Image 1-4 - Slide sequenceImage
Voiceover reference indicator
Audio cue - Calm narrationAudio
Prompt
Use the four uploaded slides in order. Generate a calm male voiceover, one short sentence per slide, at normal speaking speed. Add clean white subtitles at the bottom of the frame, synchronized with each spoken sentence. Keep the slide design readable and avoid extra decorative text.

控制重點

  • Pair each visual beat with one sentence.
  • Ask for bottom subtitles when readability matters.
  • Keep speech rate normal.
使用這個工作流程
Output
Image to Video

2.3 Speech Bubbles

Pop-style Dialogue Bubbles

Speech bubbles are useful for stylized ads, social clips, and anime-inspired scenes where the text is part of the art direction.

Formula

[Character] says "[line]" + [bubble position] + [cut order]

Reference Input
Retro snack commercial reference
Image 1 - Package and mascot styleImage
Prompt
Create a high-energy 1990s pop-anime snack commercial. Use Image 1 for the package, mascot style, and vibrant pop color palette. Add comic speech bubbles near the characters: "So crunchy!" and "One more!" The bubbles should pop in with a bounce effect, remain readable, then exit before the final product shot.

控制重點

  • Ask for bubble placement around the speaker.
  • Keep each dialogue line short.
  • Use stylized scenes for better text integration.
使用這個工作流程

03

Image Reference

3.1 Multi-angle Subject Reference / 3.2 Multi-image Reference

Output
Image to Video

3.1 Multi-angle Subject Reference

Product Shape From Multiple Angles

Use multiple product references when silhouette, material, and side details must stay stable during camera movement.

Formula

Extract [Image N subject] + generate [scene] + keep [features] stable

Reference Input
Vehicle sketch reference
Image 1 - Vehicle sketchImage
Prompt
Use Image 1 as the product reference. Preserve the core silhouette, color, reflective material, and front details. Place the object on a clean studio surface, then use a slow 180-degree orbit to reveal front, side, and rear details without changing the design.

控制重點

  • Say which details define shape, color, and material.
  • Use orbit or turntable moves for product inspection.
  • Avoid adding unrelated props.
使用這個工作流程
Output
Image to Video

3.1 Multi-angle Subject Reference

Interior Transformation From One Reference

A still interior image can become a renovation, lighting, or staging sequence when the prompt protects the original layout.

Formula

Reference [Image 1 scene] + change [state] + keep [layout] stable

Reference Input
Living room reference
Image 1 - Room layoutImage
Prompt
Use Image 1 as the room layout reference. Generate a time-lapse from raw concrete interior to a finished warm living room. Keep wall positions, window placement, and camera angle consistent. Add furniture, soft lighting, and a final light-switch moment where the room turns on.

控制重點

  • Protect layout details in the first sentence.
  • Use time-lapse wording for staged changes.
  • Name the final state clearly.
使用這個工作流程
Output
Image to Video

3.1 Multi-angle Subject Reference

Character Identity Reference

Identity references work best when the prompt separates face, wardrobe, emotion, and action.

Formula

Reference [Image N person] + generate [scene] + keep identity consistent

Reference Input
Story reveal reference
Image 1 - Character and scene moodImage
Prompt
Use Image 1 for the character identity, face shape, hair, wardrobe, and dim library mood. Start with a close-up of the character reading alone, then slowly pull back as papers move and a glowing doorway appears. Keep the character consistent while the scene changes.

控制重點

  • Put identity before action.
  • Name which details control mood.
  • Use simple movement for face stability.
使用這個工作流程
Output
Reference to Video

3.2 Multi-image Reference

Storyboard Montage With Music Mood

For a multi-image sequence, assign each image a beat and describe the emotional arc that connects them.

Formula

Reference [Image 1] + generate [story beats] + maintain [style]

Reference Input
Storyboard montage reference
Image 1 - Story and mood referenceImage
Prompt
Use Image 1 as the story and mood reference. Create a nostalgic flashback montage on 35mm film: first a warm memory, then a quiet pause, then an intimate interior detail. Use soft grain, dreamlike bokeh, warm highlights, and gentle English background music. Keep cuts rhythmic but readable.

控制重點

  • Give the source image a clear role.
  • State the transition mood between beats.
  • Keep style language consistent across beats.
使用這個工作流程

04

Video Reference

4.1 Action Reference / 4.2 Camera Movement Reference / 4.3 Effects Reference

Output
Reference to Video

4.1 Action Reference

Continuous Chase Action Reference

Use a video reference when the key value is timing, body motion, blocking, or the rhythm of a chase.

Formula

Reference [Video 1 action] + generate [new scene] + keep action details

Reference Input
Action reference video
Video 1 - Chase rhythmVideo
Prompt
Use Video 1 for the running rhythm, camera distance, obstacle timing, and main character. Generate a dusk market chase in one continuous shot: close behind the character, side-track through the crowd, then push forward as the character glances back. Add footsteps, crowd ambience, and distant shouts.

控制重點

  • Use the source video for motion and subject consistency.
  • Ask for one continuous shot when cuts are not wanted.
  • Mention sound cues for pacing.
使用這個工作流程
Output
Reference to Video

4.2 Camera Movement Reference

Steadicam Long Take Reference

Camera references are useful when the move is the product: long takes, push-ins, POV, 360 pans, or handheld rhythm.

Formula

Reference [Video 1 camera move] + generate [new subject] + keep camera path

Reference Input
Steadicam reference
Video 1 - Camera pathVideo
Prompt
Reference the camera path from Video 1: a back-following steadicam move through changing light zones. Generate a modern city walk from a warm cafe interior to a busy street and then into a subway stairwell. Keep the lighting transition smooth and do not cut away from the main subject.

控制重點

  • Say that the reference controls camera only.
  • Use lighting zones to make the move feel planned.
  • Ask for no cuts if continuity matters.
使用這個工作流程
Output
Reference to Video

4.3 Effects Reference

Transformation Effects Reference

Effects references help control particles, glows, energy trails, assembly motion, and the timing of visual transformations.

Formula

Apply [effect trajectory] to [Image 1 subject] + keep timing

Reference Input
Character reference image
Image 1 - CharacterImage
Prompt
Use Image 1 for the character design. Generate a close-up transformation scene: glowing blue runes appear, energy spreads across the face and arm with timed particles, black armor plates assemble in sequence, then the final hero pose locks in smoke.

控制重點

  • Describe the effect trajectory, not only the color.
  • Keep transformation stages in order.
  • Ask for final pose stabilization.
使用這個工作流程

05

Video Editing

5.1 Add / Remove / Modify Elements / 5.2 Video Extension / 5.3 Track Completion

Output
Reference to Video

5.1 Add / Remove / Modify Elements

Clean Up a Video While Preserving Motion

Editing prompts need a narrow target. Name the element to remove or replace, then protect motion, framing, and lighting.

Formula

Remove [element] from [Video 1] + keep [everything else] unchanged

Reference Input
Original video reference
Video 1 - Original clipVideo
Prompt
Remove all visible production mistakes from Video 1, including stray tools, tape marks, and unwanted gear. Keep the actors, hand motion, camera movement, room lighting, and timing unchanged. Do not introduce new props or change the original composition.

控制重點

  • Use a narrow edit request.
  • List what must stay unchanged.
  • Avoid asking for multiple unrelated edits at once.
使用這個工作流程
Output
Reference to Video

5.2 Video Extension

Extend After the Original Clip

Extension works when the new action naturally follows the final motion, camera angle, and tone of the original clip.

Formula

Extend [Video 1] backward / forward + [new content description]

Reference Input
Original video reference
Video 1 - Original endingVideo
Prompt
Generate content after Video 1. Continue the existing camera track and classical painting style. The main rider moves toward the blooming tree, picks two orange flowers, dismounts, and presents the flowers to the person waiting ahead. Preserve the original music mood and color palette.

控制重點

  • Say whether to extend before or after the input.
  • Continue the camera path from the source.
  • Name the new ending clearly.
使用這個工作流程
Output
Reference to Video

5.3 Track Completion

Connect First and Last Frames

Track completion is best when the first and last inputs have an obvious transformation bridge: color, light, architecture, or subject pose.

Formula

[Video 1] + [transition] + connect to [Video 2] + [transition logic]

Reference Input
First frame reference
Video 1 - Ancient sceneVideo
Last frame reference
Video 2 - Future sceneVideo
Prompt
Connect Video 1 to Video 2 in 8 seconds. Start at the ancient pyramid scene, keep the robot centered, then transform sand, stone, and amber light into a clean white future corridor. The robot design remains consistent while the environment morphs smoothly from old world to sci-fi interior.

控制重點

  • State what bridges the inputs.
  • Protect the subject through the transition.
  • Keep total reference duration within limits.
使用這個工作流程

Seedance 2.0 指南常見問題

最可靠的 Seedance 2.0 提示詞結構是什麼?

使用主體、動作、環境、美學、鏡頭和音訊。複雜影片要在開頭補充時長、比例和鏡頭順序。

什麼時候用影像參考?

當身份、產品形狀、服裝、布局、首幀或視覺風格必須穩定時,使用影像參考。

什麼時候用影片參考?

當時序、動作節奏、鏡頭路徑、手勢或特效軌跡比源素材外觀更重要時,使用影片參考。

這裡可以使用多少參考素材?

目前工作台支援最多 9 張影像、3 個影片和 3 個音訊檔案,影片和音訊時長限制見上方設定。

準備生成

把這份指南當成生成前檢查表

先選擇與你素材匹配的工作流程,再從上面的案例中改寫一條提示詞。