English日本語한국어

Promptscinematic-realisticWuxia Sword Immortal and Junior Sister Stinky Tofu Comedy

Wuxia Sword Immortal and Junior Sister Stinky Tofu Comedy

A 15-second cinematic Chinese xianxia short in three shots: two sword-fairy sisters cross a haunted ancestral shrine courtyard at night, the elder's demon-detecting compass points at the junior's bamboo food box, and the reveal is a jar of fermented tofu whose pop makes the stoic immortal cry. Uses multi-reference image-to-video with locked character faces and costumes, native Mandarin lip-synced dialogue, and a suspense-to-deadpan-comedy tonal flip.

Prompt (original, unmodified)

【整体风格】

电影级写实质感,纯古风中国仙侠美学,前半段以灵异悬疑制造紧张感,后半段反转为克制的冷面喜剧;采用古典留白构图、清冷月光、温暖灯笼光、墨蓝与陈旧象牙白色调、细腻胶片颗粒、明确的空间声音和克制的法术细节,针对 Seedance 2.0 的多参考连续性与原生音画联合生成进行设计。

【角色】

角色 ID A|剑仙师姐

剑仙师姐 @图片 1,25–30 岁的东亚女性,椭圆脸,白皙自然肤色,深色杏眼,黑色长发半挽,以白玉簪固定,身材高挑纤细,穿白色刺绣真丝汉服、半透明分层宽袖、银色腰封、玉佩和白色布靴。

角色 ID B|小师妹

小师妹 @图片 2,20–25 岁的东亚女性,圆润灵动的脸,黑发编辫,身形娇小,穿青绿色亚麻汉服、深色布腰带、木簪和黑色布鞋,双手提着一个紧闭的竹制食盒。

【镜头 1|0-5s|低角度全景缓慢跟拍】

午夜荒废的山门祖祠庭院,湿润石板倒映着两盏青铜灯,竹林被夜风压弯,香烟在深色瓦檐下缓慢飘动,一尊古老石兽正对紧闭的木质祠门,枯叶擦过地面。

同一个剑仙师姐与同一个小师妹谨慎穿过庭院,一阵若有若无的冒泡声始终跟在两人身后。

【镜头 2|5-10s|双人中景牛仔景】

同一个穿白色刺绣真丝汉服的剑仙师姐突然停下,举起同一个古老青铜寻妖罗盘,压低声音说道:“妖气就在我们之间。”

同一个罗盘的指针开始疯狂旋转,青铜铃轻轻震动,两盏灯的火苗同时朝同一个小师妹倾斜,随后指针精准指向她手中的同一个竹制食盒。

同一个剑仙师姐缓慢拔出唯一一柄银色长剑,同一个小师妹困惑地低头看向食盒;背景始终保持同一座祖祠、石兽、青铜灯、竹林和湿润庭院。

【镜头 3|10-15s|近景揭晓转极近特写】

同一个小师妹小心打开同一个竹制食盒,露出里面唯一一只密封陶罐,罐中装着发酵豆腐;罐盖伴随一声轻微的 “啵” 弹开,一股浓烈酸味让两盏灯的火苗同时颤动,也让剑仙师姐的双眼瞬间泛起泪光。

小师妹说道:“师姐,这是我腌了七日的豆腐。”

同一个剑仙师姐缓慢将长剑归鞘,面不改色地回答:“封好,莫放它出来。”

极近特写:一滴眼泪沿着她的脸颊滑落,她仍然强行维持绝对端庄的高人姿态。

【技术要求】

严格总时长 15 秒,16:9 横屏,三个连贯清楚的镜头,参考图人物面部与服装稳定,原生同步普通话对白,口型准确,香烟、真丝衣料、头发、灯笼、罗盘、陶罐和夜风运动真实自然,不生成画面字幕,始终只出现两名可见角色。

Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.

How this prompt compares

Computed from the 5,926 prompts in this library, not from this prompt alone. How the data is produced.

The techniques this prompt uses are more common in cinematic realistic prompts than in the library overall:

TechniqueIn cinematic realisticLibrary averageLift
low-key lighting22%17%1.31x

"Lift" is how much more often the technique appears in cinematic realistic prompts than across the whole library.

Across all 5,926 prompts, the techniques used here appear at: tracking 41%, close-up 40%, wide shot 26%, low-key 17%.

The 15s duration is not arbitrary: 71% of the prompts in this library that state a duration ask for exactly 15 seconds — Seedance 2.0 accepts clips up to 15 seconds, so 15s is the model's ceiling and the most common choice.

Related cases