VdoBloom
← Back

Cinematic Wuxia Swordswoman with Synchronized Echoes

Cinematic Scene ShowcaseShort Filmby @Soran · source ↗August 9, 2026

Full prompt

[Generation Mode] Seedance. First generate a 0–10 second clip, then based on that clip and its final frame, continuously extend for another 5 seconds. Total duration 15 seconds. [Screen Specifications] 16:9 widescreen, cinematic realistic texture, native synchronized Mandarin dialogue, no subtitles, only two visible characters throughout. [Overall Style] Cinematic realistic texture featuring monumental pure Chinese Xianxia architecture, restrained deadpan comedy, strong spatial sound narrative, warm sunrise piercing through cold blue-white cloud seas, weathered giant stones, dark ancient tile roofs, ivory silk, and fine film grain; the suspense is ultimately resolved through a comedic reversal within the grand scene. [Background Reference] @Image1–@Image4 used only for background and location, never for characters. Strictly preserve: giant circular celestial gate, layered rooftops of the immortal city above the clouds, mountain-scale stone pillars, dense rolling cloud seas, sunrise direction, grand spatial depth, and incredible vertical scale. [Character Settings] Character A (Senior Sister Sword Immortal): 26–30 years old, East Asian sword immortal woman, oval fair face, slender dark eyes, long black hair partially tied with a white jade hairpin, tall and slender, wearing white embroidered silk Hanfu with semi-transparent layered wide sleeves, silver waistband, jade pendant, and white cloth boots; carries a single slender silver flying sword. Character B (Junior Sister): 20–24 years old, East Asian junior sister, round and lively face, black hair in braids, small stature, wearing green linen Hanfu, dark waistband, wooden hairpin, and black cloth shoes. [Shot Design] Shot 1 (0–5s, Wide/Long Shot): 24mm aerial shot slowly pushing toward the giant celestial gate. Character A floats on a silver flying sword three meters above a stone platform, with the Junior Sister standing behind. The Senior Sister shouts deeply toward the gate: 'Guardian of the Celestial Gate, show yourself!' The circular gate immediately echoes back with clear spatial positioning: 'Show yourself—self—' Shot 2 (5–10s, Medium/Cowboy Shot): Character A lands back on the platform, Junior Sister remains behind, background stays consistent. The Senior Sister narrows her eyes, half-drawing her sword, and says coldly: 'Do not hide your head and show your tail.' The gate echoes back: 'Show your tail—tail—.' Wuxia-style zither and sword ring rise; she takes a restrained, precise defensive stance. Shot 3 (10–15s, Close-up/Extreme Close-up): The 5-second extension must continue from the final frame of the 10-second clip, maintaining total continuity of camera axis, character positions, sun direction, cloud movement, architecture, sword, and clothing. The Junior Sister walks up and says calmly: 'Sister, that is just an echo.' She then cups her hands and shouts: 'Senior Sister loves saving face the most!' The gate boisterously repeats: 'Saving face—face—.' The Senior Sister slowly sheaths her sword and whispers: 'This door is too talkative.' The gate echoes again: 'Talkative—tive—.' The shot ends on her face trying to maintain dignity but completely frozen, one eyebrow twitching slightly; the Junior Sister turns away, silently stifling a laugh. [Continuity Requirements] Generate 0-10s first, then use it as a reference to extend the last 5s. [Technical Requirements] 15s total, 16:9, sync Mandarin dialogue, spatial echo with long reverb, natural movement for clouds/silk/hair/sword, no subtitles, two characters only. [Negative Prompts] blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Original prompt

【生成模式】

Seedance
先生成 0–10 秒成片,再基于这段 0–10 秒成片及其最后一帧,连续延长后 5 秒。
总时长 15 秒。
【画面规格】
16:9 横屏
电影级写实质感
原生同步普通话对白
不生成字幕
始终只有两名可见人物

【整体风格】

电影级写实质感,采用纪念碑级纯中式仙侠建筑、克制的冷面喜剧、强烈空间声音叙事、温暖朝阳穿透清冷蓝白云海、风化巨石、深色古建瓦顶、象牙白真丝与细腻胶片颗粒;悬疑最终通过宏大场景本身完成喜剧反转。
【背景参考】
@图片1–@图片4 仅作为背景与地点参考,绝不作为人物参考。
严格保留参考图中的:
巨型圆形天门
层层叠叠的云上仙城屋顶

山岳尺度石柱

浓密翻涌云海

朝阳方向

宏大空间纵深
不可思议的垂直尺度

【角色设定】
角色 A|剑仙师姐
26–30 岁的东亚剑仙女子,椭圆白皙面庞,细长深色眼睛,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、白色布靴,唯一一柄细长银色飞剑。
角色 B|小师妹
同一个 20–24 岁的东亚小师妹,圆润灵动的脸,黑发编辫,身形娇小,穿青绿色亚麻汉服、深色腰带、木簪和黑色布鞋。
【镜头设计】
镜头 1|0–5s|全景 / 远景
24mm 航拍缓慢推向巨大天门。
角色 A 踩着同一柄银色飞剑悬浮在石台上方三米处,同一个小师妹站在后方。
剑仙师姐朝巨大天门沉声喝道:
“天门守将,现身!”

圆形巨门内部立刻传回浑厚而具有明确空间方位的回声:

“现身——身——”

镜头 2|5–10s|中景 / 牛仔景

同一个穿白色真丝汉服的剑仙师姐落回同一座石台,同一个小师妹仍然保持在后方,背景始终保持同一座巨型天门与同一片云上仙城。
剑仙师姐眯起双眼,将同一柄长剑拔出一半,冷声说道:
“莫藏头露尾。”

巨门再次以巨大回声回应:
“藏头露尾——尾——。”
英雄式古琴与剑鸣逐渐升起,她摆出克制而精准的戒备姿势。

镜头 3|10–15s|特写 / 极近特写

后 5 秒延长必须从前 10 秒成片的最后一帧原位继续,严格保持:

摄影机轴线完全连续

两名角色位置完全连续

太阳方向完全连续
云层运动完全连续

建筑结构完全连续

飞剑完全连续

服装完全连续

同一个小师妹走到她身旁,平静说道:

“师姐,那只是回声。”

随后双手拢在嘴边,对着天门大喊:

“师姐最爱面子!”
整座巨大天门立刻轰然重复:
“爱面子——子——。”
同一个剑仙师姐缓慢将长剑归鞘,低声说道:
“此门,多嘴。”
巨门马上再次回荡:
“多嘴——嘴——。”

镜头停在她努力维持端庄、高深却彻底僵住的脸上,一侧眉毛轻轻抽动;同一个小师妹转开脸,默默憋笑。

【连续性要求】

实际生成流程为:

先完整生成 0–10 秒

再把这段 0–10 秒成片及其最后一帧作为连续性参考

只延长后 5 秒

【技术要求】

总时长 15 秒

16:9 横屏

原生同步普通话对白

巨门回声具有明显方向与长混响

云海、真丝衣料、头发和飞剑运动真实自然

不生成字幕

始终只有两名可见人物
【负面词】
blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props
Generate this with Seedance 2 on VdoBloom.
Opens the image-to-video creator with this prompt and Seedance 2 pre-selected.
✨ Generate Video