Skip to content

Prompt-Details

整段视频无字幕。角色使用 [Image 1],一位约 20 岁的虚拟数字人,亚洲女性,五官精致,皮肤纹理极其逼真,神情略显疲惫。 场景:凌乱的卧室床边,柔和的暖光。背景中可以看到床上的被子隆起,一名男子正在睡觉。 服装:米色宽松卡通家居连帽衫和裤子套装。 镜头:手持自拍视角(轻微晃动以增加真实感),中景构图。 动作:开场时靠近镜头并低声耳语(营造神秘感),用拇指指向身后 → 说到“demo”时,身体恢复正常姿势并做出自信的手势 → 说到“表情和动作”时,双手托脸或抚摸头发以展示流畅度。 表情:整体基调活泼俏皮。开场呈现“八卦”表情。 完整对话(自然口语化 + 八卦/吐槽风格 + 中等语速并带有停顿):(凑近,压低声音)嘿!我是一个 AI 虚拟人,还没名字呢。自从 Seedance 2.0 发布后,我老板熬了一整晚在玩它,(指向身后)他现在还在睡呢!(恢复正常音量,自信微笑)所以现在我要向大家展示,你们现在看到的整个画面、声音、运镜,包括我的表情和动作(指着自己,歪头)……全都是我老板只用一句话就生成出来的!

How to work from this case

  • Start with the original prompt and identify which subject, camera, and mood phrases drive the output.
  • When iterating, change one variable first: lighting, motion, or emotion.
  • If references are involved, adjust framing and movement separately for more stable generations.

Editorial handling note

Public prompt pages show edited case notes instead of copy-ready raw text. High-risk, explicit, and brand- or likeness-sensitive entries are filtered from the public library.

Related Seedance prompts

15s / multi-cut STYLE: gritty crime, high sat, sharp contrast, deep shadows, warm practicals, grain STAGE: smoky retro pool hall, amber table lights, dark corners MUSIC: gritty jazz-hop ~85 BPM, dusty drums + bass hits,…
"DEMOLITION COUTURE" Creative Director DNA: Demna. The ugliness that becomes beauty. The street that becomes the runway. The apocalypse as aesthetic. 65mm IMAX. Ultra-wide Panavision — so wide the model appears…
A fluffy, moth-winged fairy pops its head out from a hollow log filled with crystallized honey drops, nibbling on a sweet amber piece. After cautiously peering around the twilight forest and seeing no one, it flutters…

Continue browsing Seedance content

After a single prompt, the next move is usually another example from the library or a guide and glossary entry that add method and terminology.