文章
如何撰寫更好的 Seedance 2.0 影片 Prompt
Seedance 2.0 是現今最強大的多模態影片模型之一:你可以在單次生成中結合文字、圖片、參考影片與音訊。但關鍵在於——成果好壞很大程度取決於 Prompt 怎麼寫,尤其是你如何告訴模型每個上傳檔案的用途。
本指南將帶你掌握能在 HiArt 上穩定產出好作品的語法與模式,無論你要做 6 秒的產品循環短片,還是 15 秒的敘事片段。
可以上傳什麼
動筆寫 Prompt 之前,先了解限制——事先規劃素材可以少做很多返工。
輸入限制
輸入類型 | 限制 | 格式 | 最大體積 |
|---|---|---|---|
圖片 | ≤ 9 | jpeg, png, webp, bmp, tiff, gif | 每張 30 MB |
影片 | ≤ 3 | mp4, mov | 每個 50 MB,總時長 2–15s |
音訊 | ≤ 3 | mp3, wav | 每個 15 MB,總時長 ≤ 15s |
文字 | 自然語言 Prompt | — | — |
合計 | ≤ 12 個檔案 | — | — |
輸出規格
- 時長:4–15 秒(可自行選擇)
- 自動生成音效與背景音樂
- 解析度:480p–720p
須知
- 上傳含真實人臉的素材會因合規要求被阻擋——請改用風格化或非寫實的參考圖。
- 使用參考影片會比純圖片生成消耗略多點數。
- 優先上傳對畫面與節奏影響最大的檔案。
@ 引用系統
每個上傳素材都會分配到一個槽位——
@Image1、@Video2、@Audio1,依此類推。模型不會自動推斷每個檔案的用途,你必須在 Prompt 中明確說明。@Image1 @Image2 @Image3 @Video1 @Video2 @Audio1
常見引用角色
用途 | 範例 |
|---|---|
首幀 | @Image1 as the first frame |
尾幀 | @Image2 as the last frame |
角色外觀 | @Image1's character as the subject |
場景/背景 | scene references @Image3 |
鏡頭運動 | reference @Video1's camera movement |
動作/編舞 | reference @Video1's action choreography |
視效/轉場 | completely reference @Video1's effects and transitions |
節奏/速度 | video rhythm references @Video1 |
背景音樂 | BGM references @Audio1 |
音效 | sound effects reference @Video3's audio |
你可以在單一 Prompt 中疊加多個角色:
@Image1's character as the subject, reference @Video1's camera movement and action choreography, BGM references @Audio1, scene references @Image2
Prompt 結構怎麼寫
好的 Prompt 通常依以下順序組成:
[Subject] + [Scene] + [Action/Motion] + [Camera] + [Timing] + [Effects/Transitions] + [Audio] + [Style/Mood]
超過 10 秒的片段,建議把動作拆成有時間標記的段落——模型會更穩定地依序執行:
0–3s: opening scene, camera, action 3–6s: mid-section development 6–10s: climax or key action 10–15s: ending shot, final text or branding
鏡頭語言速查表
Seedance 對標準電影術語反應良好。混合運鏡與景別可以獲得更精細的控制。
運鏡
術語 | 效果 |
|---|---|
Push in / Slow push | 鏡頭向主體推進 |
Pull back | 鏡頭遠離主體 |
Pan left/right | 水平搖鏡 |
Tilt up/down | 垂直搖鏡 |
Track / Follow shot | 鏡頭跟隨主體 |
Orbit / Revolve | 環繞主體拍攝 |
One-take / Oner | 一鏡到底,無剪接 |
景別
術語 | 畫面範圍 |
|---|---|
Extreme close-up | 眼睛、嘴唇或局部特寫 |
Close-up | 臉部填滿畫面 |
Medium shot | 腰部以上 |
Full shot | 全身 |
Wide / Establishing | 完整環境 |
實用範例
保持角色一致
用參考圖鎖定主體,再逐段描述場景:
The man in @Image1 walks tiredly down the hallway, slowing his steps, finally stopping at his front door. Close-up on his face — he takes a deep breath, adjusts his emotions, replaces the weariness with a relaxed expression. After entering, his daughter and a pet dog run to greet him. The interior is warm and cozy. Natural dialogue throughout.
複製參考影片的運鏡
Reference @Image1's male character. He is in @Image2's elevator. Completely reference @Video1's camera movements and facial expressions. Hitchcock zoom during the fear moment, then orbit shots of the elevator interior. Elevator doors open, follow shot walking out. Exterior scene references @Image3.
延長既有片段
生成時長要與延長長度一致(延長 5 秒 → 選擇 5 秒輸出):
Extend @Video1 by 15 seconds. 1–5s: Light and shadow slide across a wooden table through venetian blinds. 6–10s: A coffee bean drifts down from the top of frame. Camera pushes in until the screen goes black. 11–15s: Text appears — "Lucky Coffee", "Breakfast", "AM 7:00-10:00".
產品展示
Deconstruct the reference image. Static camera. Hamburger suspended and rotating mid-air. Ingredients gently separate while maintaining shape. Bun top, lettuce, tomato, beef patties, melting cheese, bun base — all descend and reassemble into a complete burger. Cheese melts and drips, lettuce and tomato dewdrops glisten.
節拍同步剪輯
@Image1 @Image2 @Image3 @Image4 @Image5 @Image6 @Image7 — match the keyframe positions and overall rhythm of @Video1 for beat-synced cuts. More dynamic character movement. Dreamlike visual style with strong tension. Adjust shot sizes and lighting to follow the music.
風格與音訊修飾語
在 Prompt 末尾加上簡短片語,引導畫面與聲音:
- 視覺:
Cinematic quality, film grain, shallow depth of field·2.35:1 widescreen, 24fps·Anime style/Photorealistic - 氛圍:
Tense and suspenseful·Warm and healing·Epic and grand - 音訊:
Background music: grand and majestic·Beat-synced transitions matching music rhythm·Voice tone reference @Video1
快速工作流程
- 決定影片類型——廣告、短劇、MV、產品、教學。
- 準備圖片、參考影片與音訊,記下每個素材對應的槽位。
- 為每個
@引用指定角色——首幀、運鏡、BGM 等。 - 依序撰寫場景:主體 → 環境 → 動作 → 鏡頭 → 時間軸。
- 加上風格與音訊修飾語,確認檔案數量與時長限制。
- 生成、檢視,下一輪再精簡含糊的描述。
常見錯誤
- 引用太模糊——只寫「reference @Video1」卻沒說明是運鏡、動作還是節奏。
- 鏡頭指令衝突——同一段同時要求固定鏡頭與環繞拍攝。
- 短片段塞太多——4 秒內切三個場景通常效果不佳。
- 上傳了卻沒指定——上傳五張圖但 Prompt 只提到兩張。
- 沒有音訊方向——音效設計是最快提升品質的方法之一。
- 時長不匹配——寫了 15 段時間軸卻選 5 秒輸出。
可直接複製的範本
15 秒產品廣告
Reference @Video1's editing style and camera transitions. Replace @Video1's product with @Image1 as the hero product. 0–3s: Product enters with dynamic rotation, close-up on texture and logo. 4–8s: Angle transitions — front, side, back — with highlight scanning light. 9–12s: Product in lifestyle usage context. 13–15s: Hero shot, brand tagline appears, music builds to resolution. Sound: Reference @Video1's background music. Add product interaction SFX.
15 秒短劇
Scene (0–5s): Close-up on reddened eyes, finger pointing accusingly, tears streaming. Dialogue (A, choking): "What exactly are you trying to take from me?" Scene (6–10s): Other character trembles, holds up evidence, steps forward. Dialogue (B): "I'm not deceiving you! This is what he entrusted to me!" Scene (11–15s): Evidence revealed. A freezes — anger shifts to shock. Sound: Urgent piano, static interference, sobbing, button click.
13 秒舞蹈片段
Have the character in @Image1 replicate the dance moves and beat-synced music from @Video1. Generate a 13-second video. Movements smooth, no stuttering or freezing.
準備試試看了嗎?在 HiArt 畫布 開啟影片節點,選擇 Seedance 2.0,上傳參考素材,貼上本指南的 Prompt。從簡單開始——一張圖、一個明確動作、一個運鏡——確認模型能穩定處理後,再逐步增加複雜度。